<?xml version="1.0" encoding="UTF-8"?>
 <rdf:RDF xmlns="http://purl.org/rss/1.0/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:cc="http://web.resource.org/cc/" xmlns:syn="http://purl.org/rss/1.0/modules/syndication/" xmlns:admin="http://webns.net/mvcb/">
  <channel rdf:about="http://pinboard.in">
    <title>Pinboard (Vaguery)</title>
    <link>https://pinboard.in/u:Vaguery/public/</link>
    <description>recent bookmarks from Vaguery</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://arxiv.org/abs/2405.21047"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2309.14564"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2310.10692"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2302.04752"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2202.00666"/>
	<rdf:li rdf:resource="https://aclanthology.org/2022.findings-acl.81/"/>
	<rdf:li rdf:resource="https://openai.com/blog/formal-math/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2105.06400"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2010.04746"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1908.03480"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.03122"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1811.01713"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2110.14207"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1809.05679"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2107.04372"/>
	<rdf:li rdf:resource="https://tedunderwood.com/2021/10/21/latent-spaces-of-culture/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2010.02256"/>
	<rdf:li rdf:resource="http://gigasquidsoftware.com/blog/2021/03/15/breakfast-with-zero-shot-nlp/"/>
	<rdf:li rdf:resource="https://alwaysalready.dreamwidth.org/5200.html"/>
	<rdf:li rdf:resource="https://pair-code.github.io/lit/"/>
	<rdf:li rdf:resource="https://culturalanalytics.org/article/17585-divergence-and-the-complexity-of-difference-in-text-and-culture"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2009.00249"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1606.05378"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.00753"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2004.14999"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2008.02250"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.08488"/>
	<rdf:li rdf:resource="https://minimaxir.com/2019/09/howto-gpt2/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2002.08795"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2002.12327"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1901.02998"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/2001.08635"/>
	<rdf:li rdf:resource="http://gigasquidsoftware.com/blog/2020/01/10/hugging-face-gpt-with-clojure/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1807.06414"/>
	<rdf:li rdf:resource="https://stanfordnlp.github.io/CoreNLP/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1910.11997"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1910.10288"/>
	<rdf:li rdf:resource="https://hcommons.org/deposits/item/hc:26955/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1607.01759"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1905.12864"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1904.08770"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1810.08237"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1608.02153"/>
	<rdf:li rdf:resource="http://languagelog.ldc.upenn.edu/nll/?p=36753"/>
	<rdf:li rdf:resource="https://www.theverge.com/2019/2/14/18224704/ai-machine-learning-language-models-read-write-openai-gpt2"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1811.01824"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1802.07089"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1811.06837"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1901.11117"/>
	<rdf:li rdf:resource="https://www.3ammagazine.com/3am/the-policemans-beard-is-algorithmically-constructed/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1805.02356"/>
	<rdf:li rdf:resource="https://www.robinsloan.com/voyages-in-sentence-space/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.04109"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1611.05896"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1710.02271"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1703.00607"/>
	<rdf:li rdf:resource="https://blog.acolyer.org/2018/02/22/dynamic-word-embeddings-for-evolving-semantic-discovery/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.08432"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.08878"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.00441"/>
	<rdf:li rdf:resource="https://github.com/mewo2/ketchum"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1710.03370"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1707.05589"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1706.04902"/>
	<rdf:li rdf:resource="http://www.andrewdavidson.com/gibberish/?companyname=Floopr"/>
	<rdf:li rdf:resource="https://blog.openai.com/unsupervised-sentiment-neuron/"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1709.06309"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1705.01991"/>
	<rdf:li rdf:resource="https://arxiv.org/abs/1608.02025"/>
	<rdf:li rdf:resource="https://jasmcole.com/2017/06/04/swype-right/"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://arxiv.org/abs/2405.21047">
    <title>[2405.21047] Grammar-Aligned Decoding</title>
    <dc:date>2026-06-10T17:21:31+00:00</dc:date>
    <link>https://arxiv.org/abs/2405.21047</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Large Language Models (LLMs) struggle with reliably generating highly structured outputs, such as program code, mathematical formulas, or well-formed markup. Constrained decoding approaches mitigate this problem by greedily restricting what tokens an LLM can output at each step to guarantee that the output matches a given constraint. Specifically, in grammar-constrained decoding (GCD), the LLM's output must follow a given grammar. In this paper, we demonstrate that GCD techniques (and in general constrained decoding techniques) can distort the LLM's distribution, leading to outputs that are grammatical but appear with likelihoods that are not proportional to the ones given by the LLM, and so ultimately are low-quality. We call the problem of aligning sampling with a grammar constraint, grammar-aligned decoding (GAD), and propose adaptive sampling with approximate expected futures (ASAp), a decoding algorithm that guarantees the output to be grammatical while provably producing outputs that match the conditional probability of the LLM's distribution conditioned on the given grammar constraint. Our algorithm uses prior sample outputs to soundly overapproximate the future grammaticality of different output prefixes. Our evaluation on code generation and structured NLP tasks shows how ASAp often produces outputs with higher likelihood (according to the LLM's distribution) than existing GCD techniques, while still enforcing the desired grammatical constraints.
]]></description>
<dc:subject>computer-science neural-networks natural-language-processing LLMs grammar constraint-satisfaction hey-I-know-this-guy GPTP2026 consider:genetic-programming</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:bff828266dd3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computer-science"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:LLMs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:grammar"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:constraint-satisfaction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:hey-I-know-this-guy"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:GPTP2026"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2309.14564">
    <title>[2309.14564] Generative Escher Meshes</title>
    <dc:date>2024-10-27T23:25:16+00:00</dc:date>
    <link>https://arxiv.org/abs/2309.14564</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper proposes a fully-automatic, text-guided generative method for producing perfectly-repeating, periodic, tile-able 2D imagery, such as the one seen on floors, mosaics, ceramics, and the work of M.C. Escher. In contrast to square texture images that are seamless when tiled, our method generates non-square tilings which comprise solely of repeating copies of the same object. It achieves this by optimizing both geometry and texture of a 2D mesh, yielding a non-square tile in the shape and appearance of the desired object, with close to no additional background details, that can tile the plane without gaps nor overlaps. We enable optimization of the tile's shape by an unconstrained, differentiable parameterization of the space of all valid tileable meshes for given boundary conditions stemming from a symmetry group. Namely, we construct a differentiable family of linear systems derived from a 2D mesh-mapping technique - Orbifold Tutte Embedding - by considering the mesh's Laplacian matrix as differentiable parameters. We prove that the solution space of these linear systems is exactly all possible valid tiling configurations, thereby providing an end-to-end differentiable representation for the entire space of valid tiles. We render the textured mesh via a differentiable renderer, and leverage a pre-trained image diffusion model to induce a loss on the resulting image, updating the mesh's parameters so as to make its appearance match the text prompt. We show our method is able to produce plausible, appealing results, with non-trivial tiles, for a variety of different periodic tiling patterns.
]]></description>
<dc:subject>tiling Escher generative-art rather-interesting purdy-pitchers something-a-little-bit-weird-tho tesselation natural-language-processing image-processing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:12c8743b860a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tiling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Escher"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:purdy-pitchers"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:something-a-little-bit-weird-tho"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tesselation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2310.10692">
    <title>[2310.10692] ACES: Generating Diverse Programming Puzzles with with Autotelic Generative Models</title>
    <dc:date>2024-09-21T14:05:02+00:00</dc:date>
    <link>https://arxiv.org/abs/2310.10692</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The ability to invent novel and interesting problems is a remarkable feature of human intelligence that drives innovation, art, and science. We propose a method that aims to automate this process by harnessing the power of state-of-the-art generative models to produce a diversity of challenging yet solvable problems, here in the context of Python programming puzzles. Inspired by the intrinsically motivated literature, Autotelic CodE Search (ACES) jointly optimizes for the diversity and difficulty of generated problems. We represent problems in a space of LLM-generated semantic descriptors describing the programming skills required to solve them (e.g. string manipulation, dynamic programming, etc.) and measure their difficulty empirically as a linearly decreasing function of the success rate of Llama-3-70B, a state-of-the-art LLM problem solver. ACES iteratively prompts a large language model to generate difficult problems achieving a diversity of target semantic descriptors (goal-directed exploration) using previously generated problems as in-context examples. ACES generates problems that are more diverse and more challenging than problems produced by baseline methods and three times more challenging than problems found in existing Python programming benchmarks on average across 11 state-of-the-art code LLMs.
]]></description>
<dc:subject>machine-learning mathematical-recreations natural-language-processing generative-models rather-interesting to-write-about consider:genetic-programming consider:performance-measures consider:ludics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4444dfd877c3/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematical-recreations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:ludics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2302.04752">
    <title>[2302.04752] Benchmarks for Automated Commonsense Reasoning: A Survey</title>
    <dc:date>2023-09-09T13:25:32+00:00</dc:date>
    <link>https://arxiv.org/abs/2302.04752</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[More than one hundred benchmarks have been developed to test the commonsense knowledge and commonsense reasoning abilities of artificial intelligence (AI) systems. However, these benchmarks are often flawed and many aspects of common sense remain untested. Consequently, we do not currently have any reliable way of measuring to what extent existing AI systems have achieved these abilities. This paper surveys the development and uses of AI commonsense benchmarks. We discuss the nature of common sense; the role of common sense in AI; the goals served by constructing commonsense benchmarks; and desirable features of commonsense benchmarks. We analyze the common flaws in benchmarks, and we argue that it is worthwhile to invest the work needed ensure that benchmark examples are consistently high quality. We survey the various methods of constructing commonsense benchmarks. We enumerate 139 commonsense benchmarks that have been developed: 102 text-based, 18 image-based, 12 video based, and 7 simulated physical environments. We discuss the gaps in the existing benchmarks and aspects of commonsense reasoning that are not addressed in any existing benchmark. We conclude with a number of recommendations for future development of commonsense AI benchmarks.
]]></description>
<dc:subject>benchmarking artificial-intelligence natural-language-processing common-sense rather-interesting review</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d15906957839/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:benchmarking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:common-sense"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:review"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2202.00666">
    <title>[2202.00666] Typical Decoding for Natural Language Generation</title>
    <dc:date>2022-07-10T11:26:07+00:00</dc:date>
    <link>https://arxiv.org/abs/2202.00666</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Despite achieving incredibly low perplexities on myriad natural language corpora, today's language models still often underperform when used to generate text. This dichotomy has puzzled the language generation community for the last few years. In this work, we posit that the abstraction of natural language as a communication channel (à la Shannon, 1948) can provide new insights into the behaviors of probabilistic language generators, e.g., why high-probability texts can be dull or repetitive. Humans use language as a means of communicating information, and do so in a simultaneously efficient and error-minimizing manner; they choose each word in a string with this (perhaps subconscious) goal in mind. We propose that generation from probabilistic models should mimic this behavior. Rather than always choosing words from the high-probability region of the distribution--which have a low Shannon information content--we sample from the set of words with information content close to the conditional entropy of our model, i.e., close to the expected information content. This decision criterion can be realized through a simple and efficient implementation, which we call typical sampling. Automatic and human evaluations show that, in comparison to nucleus and top-k sampling, typical sampling offers competitive performance in terms of quality while consistently reducing the number of degenerate repetitions.
]]></description>
<dc:subject>generative-models natural-language-processing pragmatics rather-interesting multiobjective-optimization heuristics machine-learning to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fd18d1632bfc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pragmatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multiobjective-optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://aclanthology.org/2022.findings-acl.81/">
    <title>Learning and Evaluating Character Representations in Novels - ACL Anthology</title>
    <dc:date>2022-05-28T11:51:22+00:00</dc:date>
    <link>https://aclanthology.org/2022.findings-acl.81/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We address the problem of learning fixed-length vector representations of characters in novels. Recent advances in word embeddings have proven successful in learning entity representations from short texts, but fall short on longer documents because they do not capture full book-level information. To overcome the weakness of such text-based embeddings, we propose two novel methods for representing characters: (i) graph neural network-based embeddings from a full corpus-based character network; and (ii) low-dimensional embeddings constructed from the occurrence pattern of characters in each novel. We test the quality of these character embeddings using a new benchmark suite to evaluate character representations, encompassing 12 different tasks. We show that our representation techniques combined with text-based embeddings lead to the best character representations, outperforming text-based embeddings in four tasks. Our dataset and evaluation script will be made publicly available to stimulate additional work in this area.
]]></description>
<dc:subject>digital-humanities narrative-study natural-language-processing clustering machine-learning rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f337d5d49cf4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:narrative-study"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://openai.com/blog/formal-math/">
    <title>Solving (Some) Formal Math Olympiad Problems</title>
    <dc:date>2022-05-28T11:48:54+00:00</dc:date>
    <link>https://openai.com/blog/formal-math/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We achieved a new state-of-the-art (41.2% vs 29.3%) on the miniF2F benchmark, a challenging collection of high-school olympiad problems. Our approach, which we call statement curriculum learning, consists of manually collecting a set of statements of varying difficulty levels (without proof) where the hardest statements are similar to the benchmark we target. Initially our neural prover is weak and can only prove a few of them. We iteratively search for new proofs and re-train our neural network on the newly discovered proofs, and after 8 iterations, our prover ends up being vastly superior when tested on miniF2F.]]></description>
<dc:subject>natural-language-processing mathematical-recreations proof machine-learning rather-interesting benchmarking to-write-about consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c64f1e2a78ad/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematical-recreations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:proof"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:benchmarking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2105.06400">
    <title>[2105.06400] TabLeX: A Benchmark Dataset for Structure and Content Information Extraction from Scientific Tables</title>
    <dc:date>2022-05-01T12:00:29+00:00</dc:date>
    <link>https://arxiv.org/abs/2105.06400</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Information Extraction (IE) from the tables present in scientific articles is challenging due to complicated tabular representations and complex embedded text. This paper presents TabLeX, a large-scale benchmark dataset comprising table images generated from scientific articles. TabLeX consists of two subsets, one for table structure extraction and the other for table content extraction. Each table image is accompanied by its corresponding LATEX source code. To facilitate the development of robust table IE tools, TabLeX contains images in different aspect ratios and in a variety of fonts. Our analysis sheds light on the shortcomings of current state-of-the-art table extraction models and shows that they fail on even simple table images. Towards the end, we experiment with a transformer-based existing baseline to report performance scores. In contrast to the static benchmarks, we plan to augment this dataset with more complex and diverse tables at regular intervals.
]]></description>
<dc:subject>OCR natural-language-processing training-data rather-interesting testing machine-learning to-write-about to-visualize consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:bfd70a136988/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:OCR"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:training-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:testing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-visualize"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2010.04746">
    <title>[2010.04746] Solving Historical Dictionary Codes with a Neural Language Model</title>
    <dc:date>2022-04-06T09:39:51+00:00</dc:date>
    <link>https://arxiv.org/abs/2010.04746</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We solve difficult word-based substitution codes by constructing a decoding lattice and searching that lattice with a neural language model. We apply our method to a set of enciphered letters exchanged between US Army General James Wilkinson and agents of the Spanish Crown in the late 1700s and early 1800s, obtained from the US Library of Congress. We are able to decipher 75.1% of the cipher-word tokens correctly.
]]></description>
<dc:subject>cryptography natural-language-processing rather-interesting pattern-discovery machine-learning to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c6bb647b7d13/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:cryptography"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pattern-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1908.03480">
    <title>[1908.03480] Artificially Evolved Chunks for Morphosyntactic Analysis</title>
    <dc:date>2022-04-02T12:10:57+00:00</dc:date>
    <link>https://arxiv.org/abs/1908.03480</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We introduce a language-agnostic evolutionary technique for automatically extracting chunks from dependency treebanks. We evaluate these chunks on a number of morphosyntactic tasks, namely POS tagging, morphological feature tagging, and dependency parsing. We test the utility of these chunks in a host of different ways. We first learn chunking as one task in a shared multi-task framework together with POS and morphological feature tagging. The predictions from this network are then used as input to augment sequence-labelling dependency parsing. Finally, we investigate the impact chunks have on dependency parsing in a multi-task framework. Our results from these analyses show that these chunks improve performance at different levels of syntactic abstraction on English UD treebanks and a small, diverse subset of non-English UD treebanks.
]]></description>
<dc:subject>natural-language-processing feature-construction rather-interesting evolutionary-algorithms to-understand to-write-about consider:simulation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6149ebdd2fc7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:evolutionary-algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:simulation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1705.03122">
    <title>[1705.03122] Convolutional Sequence to Sequence Learning</title>
    <dc:date>2022-03-19T12:13:52+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.03122</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on convolutional neural networks. Compared to recurrent models, computations over all elements can be fully parallelized during training and optimization is easier since the number of non-linearities is fixed and independent of the input length. Our use of gated linear units eases gradient propagation and we equip each decoder layer with a separate attention module. We outperform the accuracy of the deep LSTM setup of Wu et al. (2016) on both WMT'14 English-German and WMT'14 English-French translation at an order of magnitude faster speed, both on GPU and CPU.
]]></description>
<dc:subject>natural-language-processing translation neural-networks representation to-write-about consider:genetic-programming consider:as-a-search-operators</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ab9b002e327c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:translation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:as-a-search-operators"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1811.01713">
    <title>[1811.01713] Word Mover's Embedding: From Word2Vec to Document Embedding</title>
    <dc:date>2022-03-19T12:07:58+00:00</dc:date>
    <link>https://arxiv.org/abs/1811.01713</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[While the celebrated Word2Vec technique yields semantically rich representations for individual words, there has been relatively less success in extending to generate unsupervised sentences or documents embeddings. Recent work has demonstrated that a distance measure between documents called \emph{Word Mover's Distance} (WMD) that aligns semantically similar words, yields unprecedented KNN classification accuracy. However, WMD is expensive to compute, and it is hard to extend its use beyond a KNN classifier. In this paper, we propose the \emph{Word Mover's Embedding } (WME), a novel approach to building an unsupervised document (sentence) embedding from pre-trained word embeddings. In our experiments on 9 benchmark text classification datasets and 22 textual similarity tasks, the proposed technique consistently matches or outperforms state-of-the-art techniques, with significantly higher accuracy on problems of short length.
]]></description>
<dc:subject>natural-language-processing feature-construction performance-space-analysis predictions-as-features to-write-about to-simulate consider:visualization consider:Push-interpretation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4ce8622f2cef/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-space-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:predictions-as-features"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:Push-interpretation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2110.14207">
    <title>[2110.14207] How Much Coffee Was Consumed During EMNLP 2019? Fermi Problems: A New Reasoning Challenge for AI</title>
    <dc:date>2022-02-21T09:23:15+00:00</dc:date>
    <link>https://arxiv.org/abs/2110.14207</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Many real-world problems require the combined application of multiple reasoning abilities employing suitable abstractions, commonsense knowledge, and creative synthesis of problem-solving strategies. To help advance AI systems towards such capabilities, we propose a new reasoning challenge, namely Fermi Problems (FPs), which are questions whose answers can only be approximately estimated because their precise computation is either impractical or impossible. For example, "How much would the sea level rise if all ice in the world melted?" FPs are commonly used in quizzes and interviews to bring out and evaluate the creative reasoning abilities of humans. To do the same for AI systems, we present two datasets: 1) A collection of 1k real-world FPs sourced from quizzes and olympiads; and 2) a bank of 10k synthetic FPs of intermediate complexity to serve as a sandbox for the harder real-world challenge. In addition to question answer pairs, the datasets contain detailed solutions in the form of an executable program and supporting facts, helping in supervision and evaluation of intermediate steps. We demonstrate that even extensively fine-tuned large scale language models perform poorly on these datasets, on average making estimates that are off by two orders of magnitude. Our contribution is thus the crystallization of several unsolved AI problems into a single, new challenge that we hope will spur further advances in building systems that can reason.
]]></description>
<dc:subject>natural-language-processing artificial-intelligence rather-interesting define-your-terms benchmarking approximation to-write-about consider:representation consider:metaheuristics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d5af6eaea474/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:benchmarking"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:metaheuristics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1809.05679">
    <title>[1809.05679] Graph Convolutional Networks for Text Classification</title>
    <dc:date>2022-02-13T12:31:57+00:00</dc:date>
    <link>https://arxiv.org/abs/1809.05679</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Text classification is an important and classical problem in natural language processing. There have been a number of studies that applied convolutional neural networks (convolution on regular grid, e.g., sequence) to classification. However, only a limited number of studies have explored the more flexible graph convolutional neural networks (convolution on non-grid, e.g., arbitrary graph) for the task. In this work, we propose to use graph convolutional networks for text classification. We build a single text graph for a corpus based on word co-occurrence and document word relations, then learn a Text Graph Convolutional Network (Text GCN) for the corpus. Our Text GCN is initialized with one-hot representation for word and document, it then jointly learns the embeddings for both words and documents, as supervised by the known class labels for documents. Our experimental results on multiple benchmark datasets demonstrate that a vanilla Text GCN without any external word embeddings or knowledge outperforms state-of-the-art methods for text classification. On the other hand, Text GCN also learns predictive word and document embeddings. In addition, experimental results show that the improvement of Text GCN over state-of-the-art comparison methods become more prominent as we lower the percentage of training data, suggesting the robustness of Text GCN to less training data in text classification.
]]></description>
<dc:subject>natural-language-processing classification graphs representation rather-interesting to-understand neural-networks machine-learning to-write-about to-simulate consider:representations consider:operators</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8cf344e3303e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:graphs"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:operators"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2107.04372">
    <title>[2107.04372] A Robust Deep Ensemble Classifier for Figurative Language Detection</title>
    <dc:date>2022-02-05T13:29:23+00:00</dc:date>
    <link>https://arxiv.org/abs/2107.04372</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recognition and classification of Figurative Language (FL) is an open problem of Sentiment Analysis in the broader field of Natural Language Processing (NLP) due to the contradictory meaning contained in phrases with metaphorical content. The problem itself contains three interrelated FL recognition tasks: sarcasm, irony and metaphor which, in the present paper, are dealt with advanced Deep Learning (DL) techniques. First, we introduce a data prepossessing framework towards efficient data representation formats so that to optimize the respective inputs to the DL models. In addition, special features are extracted in order to characterize the syntactic, expressive, emotional and temper content reflected in the respective social media text references. These features aim to capture aspects of the social network user's writing method. Finally, features are fed to a robust, Deep Ensemble Soft Classifier (DESC) which is based on the combination of different DL techniques. Using three different benchmark datasets (one of them containing various FL forms) we conclude that the DESC model achieves a very good performance, worthy of comparison with relevant methodologies and state-of-the-art technologies in the challenging field of FL recognition.
]]></description>
<dc:subject>natural-language-processing metaphor pragmatics rather-interesting to-understand to-write-about consider:online-speech consider:eggcorns</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c3e38bfcbb46/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:metaphor"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pragmatics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:online-speech"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:eggcorns"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://tedunderwood.com/2021/10/21/latent-spaces-of-culture/">
    <title>Mapping the latent spaces of culture – The Stone and the Shell</title>
    <dc:date>2021-11-07T13:57:46+00:00</dc:date>
    <link>https://tedunderwood.com/2021/10/21/latent-spaces-of-culture/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The technology at the center of this roundtable doesn’t yet have a consensus name. Some observers point to an architecture, the Transformer.[1] “On the Dangers of Stochastic Parrots” focuses on size and discusses “large language models.”[2] A paper from Stanford emphasizes applications: “foundation models” are those that can adapt “to a wide range of downstream tasks.”[3] Each definition identifies a different feature of recent research as the one that matters. To keep that question open, I’ll refer here to “deep neural models of language,” a looser category.

However we define them, neural models of language are already changing the way we search the web, write code, and even play games. Academics outside computer science urgently need to discuss their role. “On the Dangers of Stochastic Parrots” deserves credit for starting the discussion—especially since publication required tenacity and courage. I am honored to be part of an event exploring its significance for the humanities.]]></description>
<dc:subject>machine-learning generative-art linguistics deep-learning natural-language-processing rather-interesting digital-humanities you-got-aesthetics-in-my-criticism</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:60a991504b48/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:linguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:you-got-aesthetics-in-my-criticism"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2010.02256">
    <title>[2010.02256] An Ensemble Approach for Automatic Structuring of Radiology Reports</title>
    <dc:date>2021-06-27T12:10:34+00:00</dc:date>
    <link>https://arxiv.org/abs/2010.02256</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Automatic structuring of electronic medical records is of high demand for clinical workflow solutions to facilitate extraction, storage, and querying of patient care information. However, developing a scalable solution is extremely challenging, specifically for radiology reports, as most healthcare institutes use either no template or department/institute specific templates. Moreover, radiologists' reporting style varies from one to another as sentences are telegraphic and do not follow general English grammar rules. We present an ensemble method that consolidates the predictions of three models, capturing various attributes of textual information for automatic labeling of sentences with section labels. These three models are: 1) Focus Sentence model, capturing context of the target sentence; 2) Surrounding Context model, capturing the neighboring context of the target sentence; and finally, 3) Formatting/Layout model, aimed at learning report formatting cues. We utilize Bi-directional LSTMs, followed by sentence encoders, to acquire the context. Furthermore, we define several features that incorporate the structure of reports. We compare our proposed approach against multiple baselines and state-of-the-art approaches on a proprietary dataset as well as 100 manually annotated radiology notes from the MIMIC-III dataset, which we are making publicly available. Our proposed approach significantly outperforms other approaches by achieving 97.1% accuracy.
]]></description>
<dc:subject>natural-language-processing specialized-generation machine-learning heuristics rather-interesting to-write-about consider:performance-measures consider:geometry-domain</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:13a8d5ab2c44/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:specialized-generation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:geometry-domain"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://gigasquidsoftware.com/blog/2021/03/15/breakfast-with-zero-shot-nlp/">
    <title>Breakfast With Zero-Shot NLP - Squid's Blog</title>
    <dc:date>2021-06-05T12:03:10+00:00</dc:date>
    <link>http://gigasquidsoftware.com/blog/2021/03/15/breakfast-with-zero-shot-nlp/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[What if I told you that you could pick up a library model and instantly classify text with arbitrary categories without any training or fine tuning?

That is exactly what we are going to do with Hugging Face’s zero-shot learning model. We will also be using libpython-clj to do this exploration without leaving the comfort of our trusty Clojure REPL.

]]></description>
<dc:subject>Clojure machine-learning natural-language-processing tutorial demo rather-interesting</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:365105e52eb1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Clojure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:demo"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://alwaysalready.dreamwidth.org/5200.html">
    <title>alwaysalready | neural net poetry process</title>
    <dc:date>2021-05-22T12:45:49+00:00</dc:date>
    <link>https://alwaysalready.dreamwidth.org/5200.html</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[I was asked about my process for creating neural net poetry, and thought it would be fun to write it out. If you want to have a look at my stuff, you can get my zines here. Everything is free but donations are gratefully appreciated.

So I have two distinct ways of generating neural net poetry, really. Going to write this as a guide in case anyone else wants to give it a try.
]]></description>
<dc:subject>generative-art neural-networks natural-language-processing algorithms artisitic-process to-write-about literariness</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:bf5699998d88/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artisitic-process"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:literariness"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://pair-code.github.io/lit/">
    <title>Language Interpretability Tool</title>
    <dc:date>2020-11-17T22:50:09+00:00</dc:date>
    <link>https://pair-code.github.io/lit/</link>
    <dc:creator>Vaguery</dc:creator><dc:subject>via:twitter rather-interesting natural-language-processing visualization statistics library to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d24060bf7770/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:twitter"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://culturalanalytics.org/article/17585-divergence-and-the-complexity-of-difference-in-text-and-culture">
    <title>Divergence and the Complexity of Difference in Text and Culture | Published in Journal of Cultural Analytics</title>
    <dc:date>2020-10-19T13:40:04+00:00</dc:date>
    <link>https://culturalanalytics.org/article/17585-divergence-and-the-complexity-of-difference-in-text-and-culture</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Measuring how much two documents differ is a basic task in the quantitative analysis oftext. Because difference is a complex, interpretive concept, researchers often operationalizedifference as distance, a mathematical function that represents documents through a metaphorof physical space. Yet the constraints of that metaphor mean that distance can only capturesome of the ways that documents can relate to each other. We show how a more generalconcept, divergence, can help solve this problem, alerting us to new ways in which documentscan relate to each other. In contrast to distance, divergence can capture enclosure relationships,where two documents differ because the patterns found in one are a partial subset of those inthe other, and the emergence of shortcuts, where two documents can be brought closer throughmediation by a third. We provide an example of this difference measure, Kullback–LeiblerDivergence, and apply it to two worked examples: the presentation of scientific argumentsin Charles Darwin’sOrigin of Species(1859) and the rhetorical structure of philosophicaltexts by Aristotle, David Hume, and Immanuel Kant. These examples illuminate the complexrelationship between time and what we refer to as an archive’s “enclosure architecture”,and show how divergence can be used in the quantitative analysis of historical, literary, andcultural texts to reveal cognitive structures invisible to spatial metaphors.]]></description>
<dc:subject>digital-humanities natural-language-processing rather-interesting define-your-terms distance to-write-about consider:metaphor consider:ontology consider:social-construction-of-data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5d6bea843432/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:distance"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:metaphor"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:ontology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:social-construction-of-data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2009.00249">
    <title>[2009.00249] PlotThread: Creating Expressive Storyline Visualizations using Reinforcement Learning</title>
    <dc:date>2020-10-13T21:03:36+00:00</dc:date>
    <link>https://arxiv.org/abs/2009.00249</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Storyline visualizations are an effective means to present the evolution of plots and reveal the scenic interactions among characters. However, the design of storyline visualizations is a difficult task as users need to balance between aesthetic goals and narrative constraints. Despite that the optimization-based methods have been improved significantly in terms of producing aesthetic and legible layouts, the existing (semi-) automatic methods are still limited regarding 1) efficient exploration of the storyline design space and 2) flexible customization of storyline layouts. In this work, we propose a reinforcement learning framework to train an AI agent that assists users in exploring the design space efficiently and generating well-optimized storylines. Based on the framework, we introduce PlotThread, an authoring tool that integrates a set of flexible interactions to support easy customization of storyline visualizations. To seamlessly integrate the AI agent into the authoring process, we employ a mixed-initiative approach where both the agent and designers work on the same canvas to boost the collaborative design of storylines. We evaluate the reinforcement learning model through qualitative and quantitative experiments and demonstrate the usage of PlotThread using a collection of use cases.
]]></description>
<dc:subject>digital-humanities natural-language-processing rather-interesting visualization to-understand to-write-about consider:nonverbal-dynamics consider:GP-traces</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8de80575bf68/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:nonverbal-dynamics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:GP-traces"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1606.05378">
    <title>[1606.05378] Simpler Context-Dependent Logical Forms via Model Projections</title>
    <dc:date>2020-10-13T20:42:45+00:00</dc:date>
    <link>https://arxiv.org/abs/1606.05378</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We consider the task of learning a context-dependent mapping from utterances to denotations. With only denotations at training time, we must search over a combinatorially large space of logical forms, which is even larger with context-dependent utterances. To cope with this challenge, we perform successive projections of the full model onto simpler models that operate over equivalence classes of logical forms. Though less expressive, we find that these simpler models are much faster and can be surprisingly effective. Moreover, they can be used to bootstrap the full model. Finally, we collected three new context-dependent semantic parsing datasets, and develop a new left-to-right parser.
]]></description>
<dc:subject>natural-language-processing machine-learning artificial-intelligence toy-problems rather-interesting to-write-about consider:representation consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:f783d25fe179/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:toy-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1705.00753">
    <title>[1705.00753] A Teacher-Student Framework for Zero-Resource Neural Machine Translation</title>
    <dc:date>2020-09-27T11:31:24+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.00753</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains. In this paper, we propose a method for zero-resource NMT by assuming that parallel sentences have close probabilities of generating a sentence in a third language. Based on this assumption, our method is able to train a source-to-target NMT model ("student") without parallel corpora available, guided by an existing pivot-to-target NMT model ("teacher") on a source-pivot parallel corpus. Experimental results show that the proposed method significantly improves over a baseline pivot-based model by +3.0 BLEU points across various language pairs.
]]></description>
<dc:subject>machine-learning algorithms rather-interesting natural-language-processing pedagogical-modeling human-in-the-loop to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b43245bfbd02/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:pedagogical-modeling"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:human-in-the-loop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2004.14999">
    <title>[2004.14999] A Matter of Framing: The Impact of Linguistic Formalism on Probing Results</title>
    <dc:date>2020-09-02T11:37:38+00:00</dc:date>
    <link>https://arxiv.org/abs/2004.14999</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Deep pre-trained contextualized encoders like BERT (Delvin et al., 2019) demonstrate remarkable performance on a range of downstream tasks. A recent line of research in probing investigates the linguistic knowledge implicitly learned by these models during pre-training. While most work in probing operates on the task level, linguistic tasks are rarely uniform and can be represented in a variety of formalisms. Any linguistics-based probing study thereby inevitably commits to the formalism used to annotate the underlying data. Can the choice of formalism affect probing results? To investigate, we conduct an in-depth cross-formalism layer probing study in role semantics. We find linguistically meaningful differences in the encoding of semantic role- and proto-role information by BERT depending on the formalism and demonstrate that layer probing can detect subtle differences between the implementations of the same linguistic formalism. Our results suggest that linguistic formalism is an important dimension in probing studies, along with the commonly used cross-task and cross-lingual experimental settings.
]]></description>
<dc:subject>natural-language-processing deep-learning looking-to-see experiment rather-interesting reverse-engineering ontology define-your-terms feature-construction</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2d972df4e4b9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:experiment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reverse-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:ontology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:define-your-terms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2008.02250">
    <title>[2008.02250] Generalized Word Shift Graphs: A Method for Visualizing and Explaining Pairwise Comparisons Between Texts</title>
    <dc:date>2020-08-29T12:47:17+00:00</dc:date>
    <link>https://arxiv.org/abs/2008.02250</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A common task in computational text analyses is to quantify how two corpora differ according to a measurement like word frequency, sentiment, or information content. However, collapsing the texts' rich stories into a single number is often conceptually perilous, and it is difficult to confidently interpret interesting or unexpected textual patterns without looming concerns about data artifacts or measurement validity. To better capture fine-grained differences between texts, we introduce generalized word shift graphs, visualizations which yield a meaningful and interpretable summary of how individual words contribute to the variation between two texts for any measure that can be formulated as a weighted average. We show that this framework naturally encompasses many of the most commonly used approaches for comparing texts, including relative frequencies, dictionary scores, and entropy-based measures like the Kullback-Leibler and Jensen-Shannon divergences. Through several case studies, we demonstrate how generalized word shift graphs can be flexibly applied across domains for diagnostic investigation, hypothesis generation, and substantive interpretation. By providing a detailed lens into textual shifts between corpora, generalized word shift graphs help computational social scientists, digital humanists, and other text analysis practitioners fashion more robust scientific narratives.
]]></description>
<dc:subject>digital-humanities natural-language-processing feature-construction visualization rather-interesting to-understand to-try consider:Reconstruction-editorials</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:0f3245501a4a/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-try"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:Reconstruction-editorials"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1705.08488">
    <title>[1705.08488] Second-Order Word Embeddings from Nearest Neighbor Topological Features</title>
    <dc:date>2020-07-22T15:25:52+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.08488</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We introduce second-order vector representations of words, induced from nearest neighborhood topological features in pre-trained contextual word embeddings. We then analyze the effects of using second-order embeddings as input features in two deep natural language processing models, for named entity recognition and recognizing textual entailment, as well as a linear model for paraphrase recognition. Surprisingly, we find that nearest neighbor information alone is sufficient to capture most of the performance benefits derived from using pre-trained word embeddings. Furthermore, second-order embeddings are able to handle highly heterogeneous data better than first-order representations, though at the cost of some specificity. Additionally, augmenting contextual embeddings with second-order information further improves model performance in some cases. Due to variance in the random initializations of word embeddings, utilizing nearest neighbor features from multiple first-order embedding samples can also contribute to downstream performance gains. Finally, we identify intriguing characteristics of second-order embedding spaces for further research, including much higher density and different semantic interpretations of cosine similarity.
]]></description>
<dc:subject>natural-language-processing representation performance-space-analysis dimension-reduction machine-learning nearest-neighbors inference</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b0906007360d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-space-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nearest-neighbors"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inference"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://minimaxir.com/2019/09/howto-gpt2/">
    <title>How To Make Custom AI-Generated Text With GPT-2 | Max Woolf's Blog</title>
    <dc:date>2020-05-02T12:28:14+00:00</dc:date>
    <link>https://minimaxir.com/2019/09/howto-gpt2/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Neil Shepperd created a fork of OpenAI’s repo which contains additional code to allow finetuning the existing OpenAI model on custom datasets. A notebook was created soon after, which can be copied into Google Colaboratory and clones Shepperd’s repo to finetune GPT-2 backed by a free GPU. From there, the proliferation of GPT-2 generated text took off: researchers such as Gwern Branwen made GPT-2 Poetry and Janelle Shane made GPT-2 Dungeons and Dragons character bios.

I waited to see if anyone would make a tool to help streamline this finetuning and text generation workflow, a la textgenrnn which I had made for recurrent neural network-based text generation. Months later, no one did. So I did it myself. Enter gpt-2-simple, a Python package which wraps Shepperd’s finetuning code in a functional interface and adds many utilities for model management and generation control.

]]></description>
<dc:subject>GPT-2 natural-language-processing text-generation machine-learning tutorial rather-interesting to-simulate to-use consider:OCR</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a0e3105bd787/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:GPT-2"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:text-generation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:tutorial"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-use"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:OCR"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2002.08795">
    <title>[2002.08795] How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents</title>
    <dc:date>2020-05-02T11:37:41+00:00</dc:date>
    <link>https://arxiv.org/abs/2002.08795</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Text-based games -- in which an agent interacts with the world through textual natural language -- present us with the problem of combinatorially-sized action-spaces. Most current reinforcement learning algorithms are not capable of effectively handling such a large number of possible actions per turn. Poor sample efficiency, consequently, results in agents that are unable to pass bottleneck states, where they are unable to proceed because they do not see the right action sequence to pass the bottleneck enough times to be sufficiently reinforced. Building on prior work using knowledge graphs in reinforcement learning, we introduce two new game state exploration strategies. We compare our exploration strategies against strong baselines on the classic text-adventure game, Zork1, where prior agent have been unable to get past a bottleneck where the agent is eaten by a Grue.
]]></description>
<dc:subject>machine-learning games natural-language-processing rather-interesting to-simulate to-write-about consider:representation consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:117297c5f844/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:games"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2002.12327">
    <title>[2002.12327] A Primer in BERTology: What we know about how BERT works</title>
    <dc:date>2020-04-22T20:41:05+00:00</dc:date>
    <link>https://arxiv.org/abs/2002.12327</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Transformer-based models are now widely used in NLP, but we still do not understand a lot about their inner workings. This paper describes what is known to date about the famous BERT model (Devlin et al. 2019), synthesizing over 40 analysis studies. We also provide an overview of the proposed modifications to the model and its training regime. We then outline the directions for further research.]]></description>
<dc:subject>natural-language-processing machine-learning looking-to-see models reverse-engineering rather-interesting to-write-about to-try consider:genetic-programming</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:dfbbf1627ceb/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:reverse-engineering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-try"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:genetic-programming"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1901.02998">
    <title>[1901.02998] Sentence Rewriting for Semantic Parsing</title>
    <dc:date>2020-03-20T16:33:56+00:00</dc:date>
    <link>https://arxiv.org/abs/1901.02998</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[A major challenge of semantic parsing is the vocabulary mismatch problem between natural language and target ontology. In this paper, we propose a sentence rewriting based semantic parsing method, which can effectively resolve the mismatch problem by rewriting a sentence into a new form which has the same structure with its target logical form. Specifically, we propose two sentence-rewriting methods for two common types of mismatch: a dictionary-based method for 1-N mismatch and a template-based method for N-1 mismatch. We evaluate our entence rewriting based semantic parser on the benchmark semantic parsing dataset -- WEBQUESTIONS. Experimental results show that our system outperforms the base system with a 3.4% gain in F1, and generates logical forms more accurately and parses sentences more robustly.
]]></description>
<dc:subject>natural-language-processing rewriting-systems artificial-intelligence representation algorithms rather-interesting to-write-about to-simulate consider:interactive-grammar</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b1223bc5fd7e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rewriting-systems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:interactive-grammar"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/2001.08635">
    <title>[2001.08635] A Study of the Tasks and Models in Machine Reading Comprehension</title>
    <dc:date>2020-03-19T15:42:10+00:00</dc:date>
    <link>https://arxiv.org/abs/2001.08635</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[To provide a survey on the existing tasks and models in Machine Reading Comprehension (MRC), this report reviews: 1) the dataset collection and performance evaluation of some representative simple-reasoning and complex-reasoning MRC tasks; 2) the architecture designs, attention mechanisms, and performance-boosting approaches for developing neural-network-based MRC models; 3) some recently proposed transfer learning approaches to incorporating text-style knowledge contained in external corpora into the neural networks of MRC models; 4) some recently proposed knowledge base encoding approaches to incorporating graph-style knowledge contained in external knowledge bases into the neural networks of MRC models. Besides, according to what has been achieved and what are still deficient, this report also proposes some open problems for the future research.
]]></description>
<dc:subject>natural-language-processing artificial-intelligence rather-interesting survey to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:82f8e5b0a147/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:survey"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://gigasquidsoftware.com/blog/2020/01/10/hugging-face-gpt-with-clojure/">
    <title>Hugging Face GPT With Clojure - Squid's Blog</title>
    <dc:date>2020-02-19T11:47:45+00:00</dc:date>
    <link>http://gigasquidsoftware.com/blog/2020/01/10/hugging-face-gpt-with-clojure/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[You can now interop with ANY python library.


I know. It’s overwhelming. It took a bit for me to come to grips with it too.


Let’s take an example of something that I’ve always wanted to do and have struggled with mightly finding a way to do it in Clojure:
I want to use the latest cutting edge GPT2 code out there to generate text.

Right now, that library is Hugging Face Transformers.


Get ready. We will wrap that sweet hugging face code in Clojure parens!

]]></description>
<dc:subject>machine-learning Clojure interop natural-language-processing rather-interesting library to-understand to-follow-along to-write-about consider:scraping-for-data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:aeadf35f2716/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Clojure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interop"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-follow-along"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:scraping-for-data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1807.06414">
    <title>[1807.06414] Combining a Context Aware Neural Network with a Denoising Autoencoder for Measuring String Similarities</title>
    <dc:date>2020-02-16T13:08:12+00:00</dc:date>
    <link>https://arxiv.org/abs/1807.06414</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Measuring similarities between strings is central for many established and fast growing research areas including information retrieval, biology, and natural language processing. The traditional approach for string similarity measurements is to define a metric over a word space that quantifies and sums up the differences between characters in two strings. The state-of-the-art in the area has, surprisingly, not evolved much during the last few decades. The majority of the metrics are based on a simple comparison between character and character distributions without consideration for the context of the words. This paper proposes a string metric that encompasses similarities between strings based on (1) the character similarities between the words including. Non-Standard and standard spellings of the same words, and (2) the context of the words. Our proposal is a neural network composed of a denoising autoencoder and what we call a context encoder specifically designed to find similarities between the words based on their context. The experimental results show that the resulting metrics succeeds in 85.4\% of the cases in finding the correct version of a non-standard spelling among the closest words, compared to 63.2\% with the established Normalised-Levenshtein distance. Besides, we show that words used in similar context are with our approach calculated to be similar than words with different contexts, which is a desirable property missing in established string metrics.
]]></description>
<dc:subject>feature-construction machine-learning clustering natural-language-processing rather-interesting to-simulate to-write-about consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:e79ce779e77d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://stanfordnlp.github.io/CoreNLP/">
    <title>Stanford CoreNLP – Natural language software | Stanford CoreNLP</title>
    <dc:date>2020-01-21T14:41:06+00:00</dc:date>
    <link>https://stanfordnlp.github.io/CoreNLP/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Stanford CoreNLP provides a set of human language technology tools. It can give the base forms of words, their parts of speech, whether they are names of companies, people, etc., normalize dates, times, and numeric quantities, mark up the structure of sentences in terms of phrases and syntactic dependencies, indicate which noun phrases refer to the same entities, indicate sentiment, extract particular or open-class relations between entity mentions, get the quotes people said, etc.

]]></description>
<dc:subject>natural-language-processing library Clojure to-understand to-use to-write-about notesapp</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5ffcb7f27c8e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:Clojure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-use"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:notesapp"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1910.11997">
    <title>[1910.11997] Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens</title>
    <dc:date>2020-01-19T01:22:49+00:00</dc:date>
    <link>https://arxiv.org/abs/1910.11997</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Mellotron is a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data. By explicitly conditioning on rhythm and continuous pitch contours from an audio signal or music score, Mellotron is able to generate speech in a variety of styles ranging from read speech to expressive speech, from slow drawls to rap and from monotonous voice to singing voice. Unlike other methods, we train Mellotron using only read speech data without alignments between text and audio. We evaluate our models using the LJSpeech and LibriTTS datasets. We provide F0 Frame Errors and synthesized samples that include style transfer from other speakers, singers and styles not seen during training, procedural manipulation of rhythm and pitch and choir synthesis.
]]></description>
<dc:subject>speech-synthesis natural-language-processing style-transfer machine-learning neural-networks rather-interesting consider:performance-measures to-simulate time-series dimension-reduction</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:091458f6f457/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:speech-synthesis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:style-transfer"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:dimension-reduction"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1910.10288">
    <title>[1910.10288] Location-Relative Attention Mechanisms For Robust Long-Form Speech Synthesis</title>
    <dc:date>2020-01-10T15:52:55+00:00</dc:date>
    <link>https://arxiv.org/abs/1910.10288</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Despite the ability to produce human-level speech for in-domain text, attention-based end-to-end text-to-speech (TTS) systems suffer from text alignment failures that increase in frequency for out-of-domain text. We show that these failures can be addressed using simple location-relative attention mechanisms that do away with content-based query/key comparisons. We compare two families of attention mechanisms: location-relative GMM-based mechanisms and additive energy-based mechanisms. We suggest simple modifications to GMM-based attention that allow it to align quickly and consistently during training, and introduce a new location-relative attention mechanism to the additive energy-based family, called Dynamic Convolution Attention (DCA). We compare the various mechanisms in terms of alignment speed and consistency during training, naturalness, and ability to generalize to long utterances, and conclude that GMM attention and DCA can generalize to very long utterances, while preserving naturalness for shorter, in-domain utterances.
]]></description>
<dc:subject>speech-synthesis natural-language-processing neural-networks recurrent-networks algorithms feature-construction rather-interesting to-write-about to-simulate</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:d6b5b60fc46c/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:speech-synthesis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:recurrent-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://hcommons.org/deposits/item/hc:26955/">
    <title>NovelTM Datasets for English-Language Fiction, 1700-2009 | hc:26955 | Humanities CORE</title>
    <dc:date>2019-10-13T11:37:59+00:00</dc:date>
    <link>https://hcommons.org/deposits/item/hc:26955/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This report describes a collection of 210,305 volumes of fiction that researchers are encouraged to borrow for their own work. Alternately, readers can simply browse the report as a description of English-language fiction in HathiTrust Digital Library. For instance, how does the proportion of fiction written by British authors or by women change across time? We also divide nineteenth- and twentieth-century fiction into seven subsets with different emphases (for instance, one where men and women are represented equally, and one composed of only the most prominent and widely-held books). Comparing the pictures produced by these different samples allows us to assess the fragility of recent quantitative arguments about literary history. Preprint version of an article to appear in the Journal of Cultural Analytics.]]></description>
<dc:subject>digital-humanities open-data natural-language-processing rather-interesting to-use digitization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8d34470e8018/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:open-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-use"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digitization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1607.01759">
    <title>[1607.01759] Bag of Tricks for Efficient Text Classification</title>
    <dc:date>2019-09-29T10:44:19+00:00</dc:date>
    <link>https://arxiv.org/abs/1607.01759</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper explores a simple and efficient baseline for text classification. Our experiments show that our fast text classifier fastText is often on par with deep learning classifiers in terms of accuracy, and many orders of magnitude faster for training and evaluation. We can train fastText on more than one billion words in less than ten minutes using a standard multicore~CPU, and classify half a million sentences among~312K classes in less than a minute.
]]></description>
<dc:subject>natural-language-processing text-mining classification machine-learning heuristics representation rather-interesting neural-networks to-simulate consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:37eb163ef7f7/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:text-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:classification"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:heuristics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-simulate"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1905.12864">
    <title>[1905.12864] Interpretable Adversarial Training for Text</title>
    <dc:date>2019-09-28T10:49:54+00:00</dc:date>
    <link>https://arxiv.org/abs/1905.12864</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Generating high-quality and interpretable adversarial examples in the text domain is a much more daunting task than it is in the image domain. This is due partly to the discrete nature of text, partly to the problem of ensuring that the adversarial examples are still probable and interpretable, and partly to the problem of maintaining label invariance under input perturbations. In order to address some of these challenges, we introduce sparse projected gradient descent (SPGD), a new approach to crafting interpretable adversarial examples for text. SPGD imposes a directional regularization constraint on input perturbations by projecting them onto the directions to nearby word embeddings with highest cosine similarities. This constraint ensures that perturbations move each word embedding in an interpretable direction (i.e., towards another nearby word embedding). Moreover, SPGD imposes a sparsity constraint on perturbations at the sentence level by ignoring word-embedding perturbations whose norms are below a certain threshold. This constraint ensures that our method changes only a few words per sequence, leading to higher quality adversarial examples. Our experiments with the IMDB movie review dataset show that the proposed SPGD method improves adversarial example interpretability and likelihood (evaluated by average per-word perplexity) compared to state-of-the-art methods, while suffering little to no loss in training performance.
]]></description>
<dc:subject>natural-language-processing machine-learning coevolution adversarial-learning rather-interesting consider:looking-to-see consider:feature-construction the-mangle-in-practice</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:856e8c707344/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:coevolution"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:adversarial-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:the-mangle-in-practice"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1904.08770">
    <title>[1904.08770] An Empirical Evaluation of Text Representation Schemes on Multilingual Social Web to Filter the Textual Aggression</title>
    <dc:date>2019-09-23T10:15:24+00:00</dc:date>
    <link>https://arxiv.org/abs/1904.08770</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper attempt to study the effectiveness of text representation schemes on two tasks namely: User Aggression and Fact Detection from the social media contents. In User Aggression detection, The aim is to identify the level of aggression from the contents generated in the Social media and written in the English, Devanagari Hindi and Romanized Hindi. Aggression levels are categorized into three predefined classes namely: `Non-aggressive`, `Overtly Aggressive`, and `Covertly Aggressive`. During the disaster-related incident, Social media like, Twitter is flooded with millions of posts. In such emergency situations, identification of factual posts is important for organizations involved in the relief operation. We anticipated this problem as a combination of classification and Ranking problem. This paper presents a comparison of various text representation scheme based on BoW techniques, distributed word/sentence representation, transfer learning on classifiers. Weighted F1 score is used as a primary evaluation metric. Results show that text representation using BoW performs better than word embedding on machine learning classifiers. While pre-trained Word embedding techniques perform better on classifiers based on deep neural net. Recent transfer learning model like ELMO, ULMFiT are fine-tuned for the Aggression classification task. However, results are not at par with pre-trained word embedding model. Overall, word embedding using fastText produce best weighted F1-score than Word2Vec and Glove. Results are further improved using pre-trained vector model. Statistical significance tests are employed to ensure the significance of the classification results. In the case of lexically different test Dataset, other than training Dataset, deep neural models are more robust and perform substantially better than machine learning classifiers.
]]></description>
<dc:subject>text-analysis text-processing sentiment-analysis natural-language-processing social-media to-write-about consider:feature-discovery machine-learning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:8a0e1138415d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:text-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:text-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:sentiment-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:social-media"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1810.08237">
    <title>[1810.08237] Large-scale Hierarchical Alignment for Data-driven Text Rewriting</title>
    <dc:date>2019-08-06T10:14:16+00:00</dc:date>
    <link>https://arxiv.org/abs/1810.08237</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We propose a simple unsupervised method for extracting pseudo-parallel monolingual sentence pairs from comparable corpora representative of two different text styles, such as news articles and scientific papers. Our approach does not require a seed parallel corpus, but instead relies solely on hierarchical search over pre-trained embeddings of documents and sentences. We demonstrate the effectiveness of our method through automatic and extrinsic evaluation on text simplification from the normal to the Simple Wikipedia. We show that pseudo-parallel sentences extracted with our method not only supplement existing parallel data, but can even lead to competitive performance on their own.
]]></description>
<dc:subject>natural-language-processing text-mining translation rather-interesting algorithms representation machine-learning clustering unsupervised-learning to-understand</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ef18c7dc07ba/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:text-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:translation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:clustering"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:unsupervised-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1608.02153">
    <title>[1608.02153] OCR of historical printings with an application to building diachronic corpora: A case study using the RIDGES herbal corpus</title>
    <dc:date>2019-08-03T12:49:20+00:00</dc:date>
    <link>https://arxiv.org/abs/1608.02153</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This article describes the results of a case study that applies Neural Network-based Optical Character Recognition (OCR) to scanned images of books printed between 1487 and 1870 by training the OCR engine OCRopus [@breuel2013high] on the RIDGES herbal text corpus [@OdebrechtEtAlSubmitted]. Training specific OCR models was possible because the necessary *ground truth* is available as error-corrected diplomatic transcriptions. The OCR results have been evaluated for accuracy against the ground truth of unseen test sets. Character and word accuracies (percentage of correctly recognized items) for the resulting machine-readable texts of individual documents range from 94% to more than 99% (character level) and from 76% to 97% (word level). This includes the earliest printed books, which were thought to be inaccessible by OCR methods until recently. Furthermore, OCR models trained on one part of the corpus consisting of books with different printing dates and different typesets *(mixed models)* have been tested for their predictive power on the books from the other part containing yet other fonts, mostly yielding character accuracies well above 90%. It therefore seems possible to construct generalized models trained on a range of fonts that can be applied to a wide variety of historical printings still giving good results. A moderate postcorrection effort of some pages will then enable the training of individual models with even better accuracies. Using this method, diachronic corpora including early printings can be constructed much faster and cheaper than by manual transcription. The OCR methods reported here open up the possibility of transforming our printed textual cultural heritage into electronic text by largely automatic means, which is a prerequisite for the mass conversion of scanned books.
]]></description>
<dc:subject>OCR image-processing natural-language-processing algorithms machine-learning rather-interesting commodity-software digital-humanities to-write-about consider:swarms consider:stochastic-resonance</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:105d3a25b2ab/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:OCR"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:commodity-software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:swarms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:stochastic-resonance"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://languagelog.ldc.upenn.edu/nll/?p=36753">
    <title>Language Log » o ai aaa oa ueui</title>
    <dc:date>2019-03-30T12:43:56+00:00</dc:date>
    <link>http://languagelog.ldc.upenn.edu/nll/?p=36753</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Some useful advice:

aiauee uiiu ouio ea ao eueaiueoieui i eaoeoi e uoioooaaeoeiua iuo ui ioeuui aaio oiaeauau eii eoio iiioee oui oueoaueuaaiuu uee e oiiae ia uu eao

let's see you while you are here to go to your friends and keep them in touch with you here and then you will be able to keep your eye on it.]]></description>
<dc:subject>machine-learning translation natural-language-processing linguistics a-guess-is-as-good-as-a-try</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:44a4ee7cbb50/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:translation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:linguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:a-guess-is-as-good-as-a-try"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.theverge.com/2019/2/14/18224704/ai-machine-learning-language-models-read-write-openai-gpt2">
    <title>OpenAI unveils multitalented AI that writes, translates, and slanders - The Verge</title>
    <dc:date>2019-02-23T12:44:14+00:00</dc:date>
    <link>https://www.theverge.com/2019/2/14/18224704/ai-machine-learning-language-models-read-write-openai-gpt2</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The success of these newer, deeper language models has caused a stir in the AI community. Researcher Sebastian Ruder compares their success to advances made in computer vision in the early 2010s. At this time, deep learning helped algorithms make huge strides in their ability to identify and categorize visual data, kickstarting the current AI boom. Without these advances, a whole range of technologies — from self-driving cars to facial recognition and AI-enhanced photography — would be impossible today. This latest leap in language understanding could have similar, transformational effects.

One reason to be excited about GPT-2, says Ani Kembhavi, a researcher at the Allen Institute for Artificial Intelligence, is that predicting text can be thought of as an “uber-task” for computers: a broad challenge that, once solved, will open a floodgate of intelligence.

“Asking the time or getting directions can both be thought of as question-answering tasks that involve predicting text,” Kembhavi tells The Verge. “So, hypothetically, if you train a good enough question-answering model, it can potentially do anything.”

Take GPT-2’s ability to translate text from English to French, for example. Usually, translation algorithms are fed hundreds of thousands of phrases in relevant languages, and the networks themselves are structured in such a way that they process data by converting input X into output Y. This data and network architecture give these systems the tools they need to progress on this task the same way snow chains help cars get a grip on icy roads.

]]></description>
<dc:subject>natural-language-processing openAI machine-learning rather-interesting to-write-about representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:3fb7703523ff/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:openAI"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1811.01824">
    <title>[1811.01824] Structured Neural Summarization</title>
    <dc:date>2019-02-23T12:09:06+00:00</dc:date>
    <link>https://arxiv.org/abs/1811.01824</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input. Based on the promising results of graph neural networks on highly structured data, we develop a framework to extend existing sequence encoders with a graph component that can reason about long-distance relationships in weakly structured data such as text. In an extensive evaluation, we show that the resulting hybrid sequence-graph models outperform both pure sequence models as well as pure graph models on a range of summarization tasks.
]]></description>
<dc:subject>natural-language-processing summarization complicated algorithms neural-networks to-write-about consider:performance-measures consider:benchmarks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:46e23ca875a1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:summarization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:complicated"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:benchmarks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1802.07089">
    <title>[1802.07089] Attentive Tensor Product Learning</title>
    <dc:date>2019-02-13T11:34:44+00:00</dc:date>
    <link>https://arxiv.org/abs/1802.07089</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper proposes a new architecture - Attentive Tensor Product Learning (ATPL) - to represent grammatical structures in deep learning models. ATPL is a new architecture to bridge this gap by exploiting Tensor Product Representations (TPR), a structured neural-symbolic model developed in cognitive science, aiming to integrate deep learning with explicit language structures and rules. The key ideas of ATPL are: 1) unsupervised learning of role-unbinding vectors of words via TPR-based deep neural network; 2) employing attention modules to compute TPR; and 3) integration of TPR with typical deep learning architectures including Long Short-Term Memory (LSTM) and Feedforward Neural Network (FFNN). The novelty of our approach lies in its ability to extract the grammatical structure of a sentence by using role-unbinding vectors, which are obtained in an unsupervised manner. This ATPL approach is applied to 1) image captioning, 2) part of speech (POS) tagging, and 3) constituency parsing of a sentence. Experimental results demonstrate the effectiveness of the proposed approach.
]]></description>
<dc:subject>machine-learning representation natural-language-processing recurrent-networks time-series to-understand data-fusion to-write-about consider:parsing-GP-results</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c917331e423b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:recurrent-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-fusion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:parsing-GP-results"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1811.06837">
    <title>[1811.06837] A Grammar-Based Structural CNN Decoder for Code Generation</title>
    <dc:date>2019-02-13T11:28:56+00:00</dc:date>
    <link>https://arxiv.org/abs/1811.06837</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Code generation maps a program description to executable source code in a programming language. Existing approaches mainly rely on a recurrent neural network (RNN) as the decoder. However, we find that a program contains significantly more tokens than a natural language sentence, and thus it may be inappropriate for RNN to capture such a long sequence. In this paper, we propose a grammar-based structural convolutional neural network (CNN) for code generation. Our model generates a program by predicting the grammar rules of the programming language; we design several CNN modules, including the tree-based convolution and pre-order convolution, whose information is further aggregated by dedicated attentive pooling layers. Experimental results on the HearthStone benchmark dataset show that our CNN code generator significantly outperforms the previous state-of-the-art method by 5 percentage points; additional experiments on several semantic parsing tasks demonstrate the robustness of our model. We also conduct in-depth ablation test to better understand each component of our model.
]]></description>
<dc:subject>rather-interesting machine-learning generative-models natural-language-processing software-synthesis structured-data to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fb578f891775/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:software-synthesis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:structured-data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1901.11117">
    <title>[1901.11117] The Evolved Transformer</title>
    <dc:date>2019-02-08T15:42:12+00:00</dc:date>
    <link>https://arxiv.org/abs/1901.11117</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Recent works have highlighted the strengths of the Transformer architecture for dealing with sequence tasks. At the same time, neural architecture search has advanced to the point where it can outperform human-designed models. The goal of this work is to use architecture search to find a better Transformer architecture. We first construct a large search space inspired by the recent advances in feed-forward sequential models and then run evolutionary architecture search, seeding our initial population with the Transformer. To effectively run this search on the computationally expensive WMT 2014 English-German translation task, we develop the progressive dynamic hurdles method, which allows us to dynamically allocate more resources to more promising candidate models. The architecture found in our experiments - the Evolved Transformer - demonstrates consistent improvement over the Transformer on four well-established language tasks: WMT 2014 English-German, WMT 2014 English-French, WMT 2014 English-Czech and LM1B. At big model size, the Evolved Transformer is twice as efficient as the Transformer in FLOPS without loss in quality. At a much smaller - mobile-friendly - model size of ~7M parameters, the Evolved Transformer outperforms the Transformer by 0.7 BLEU on WMT'14 English-German.
]]></description>
<dc:subject>machine-learning natural-language-processing deep-learning neural-networks wheel-2.0-again</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4ed043000b7f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:wheel-2.0-again"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.3ammagazine.com/3am/the-policemans-beard-is-algorithmically-constructed/">
    <title>The Policeman’s Beard is Algorithmically Constructed - 3:AM Magazine</title>
    <dc:date>2018-10-14T12:33:05+00:00</dc:date>
    <link>https://www.3ammagazine.com/3am/the-policemans-beard-is-algorithmically-constructed/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[The Policeman’s Beard is an aggressively egotistical book. Measuring 22.6 x 20.3 x 1.5 centimetres, it dwarfs many of its neighbours on the shelf. Its paper cover is bright red, with a doctored photograph of a man who occupies a sturdy frame as he glares at prospective readers. The book begs to be handled, while at the same time warning readers to approach with caution.

And caution is indeed warranted, for The Policeman’s Beard and Racter are puzzling. In some ways, Racter does adhere to the modern conception of authorship. As with any human writer, Racter’s code interacts with a world—albeit a limited world that has been consciously created by its programmers—as a source of information, and remixes content to create unique texts. Yet Racter is rigid, using fixed functions to complete a particular task. The program cannot interpret that which it produces and, indeed, not until a human interprets Racter’s output can it be assigned any cultural value.

]]></description>
<dc:subject>generative-art nanohistory natural-language-processing I-remember-it-well the-mangle-in-practice to-write-about literary-criticism computational-criticism performative-writing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:da34b369ea28/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-art"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nanohistory"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:I-remember-it-well"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:the-mangle-in-practice"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:literary-criticism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:computational-criticism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performative-writing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1805.02356">
    <title>[1805.02356] Multimodal Machine Translation with Reinforcement Learning</title>
    <dc:date>2018-05-26T14:09:43+00:00</dc:date>
    <link>https://arxiv.org/abs/1805.02356</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Multimodal machine translation is one of the applications that integrates computer vision and language processing. It is a unique task given that in the field of machine translation, many state-of-the-arts algorithms still only employ textual information. In this work, we explore the effectiveness of reinforcement learning in multimodal machine translation. We present a novel algorithm based on the Advantage Actor-Critic (A2C) algorithm that specifically cater to the multimodal machine translation task of the EMNLP 2018 Third Conference on Machine Translation (WMT18). We experiment our proposed algorithm on the Multi30K multilingual English-German image description dataset and the Flickr30K image entity dataset. Our model takes two channels of inputs, image and text, uses translation evaluation metrics as training rewards, and achieves better results than supervised learning MLE baseline models. Furthermore, we discuss the prospects and limitations of using reinforcement learning for machine translation. Our experiment results suggest a promising reinforcement learning solution to the general task of multimodal sequence to sequence learning.
]]></description>
<dc:subject>natural-language-processing machine-learning multitask-learning rather-interesting algorithms performance-measure to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:1bc18b5fe284/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:multitask-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:performance-measure"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://www.robinsloan.com/voyages-in-sentence-space/">
    <title>Voyages in sentence space</title>
    <dc:date>2018-03-31T12:29:10+00:00</dc:date>
    <link>https://www.robinsloan.com/voyages-in-sentence-space/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Imagine a sentence. “I went looking for adventure.”

Imagine another one. “I never returned.”

Now imagine a sentence gradient between them—not a story, but a smooth interpolation of meaning. This is a weird thing to ask for! I’d never even bothered to imagine an interpolation between sentences before encountering the idea in a recent academic paper. But as soon as I did, I found it captivating, both for the thing itself—a sentence… gradient?—and for the larger artifact it suggested: a dense cloud of sentences, all related; a space you might navigate and explore.]]></description>
<dc:subject>natural-language-processing rather-interesting via:several algorithms feature-extraction interpolation to-write-about consider:embedding-space</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:534ef4a035d0/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:via:several"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:interpolation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:embedding-space"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1709.04109">
    <title>[1709.04109] Empower Sequence Labeling with Task-Aware Neural Language Model</title>
    <dc:date>2018-03-31T12:23:56+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.04109</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Linguistic sequence labeling is a general modeling approach that encompasses a variety of problems, such as part-of-speech tagging and named entity recognition. Recent advances in neural networks (NNs) make it possible to build reliable models without handcrafted features. However, in many cases, it is hard to obtain sufficient annotations to train these models. In this study, we develop a novel neural framework to extract abundant knowledge hidden in raw texts to empower the sequence labeling task. Besides word-level knowledge contained in pre-trained word embeddings, character-aware neural language models are incorporated to extract character-level knowledge. Transfer learning techniques are further adopted to mediate different components and guide the language model towards the key knowledge. Comparing to previous methods, these task-specific knowledge allows us to adopt a more concise model and conduct more efficient training. Different from most transfer learning methods, the proposed framework does not rely on any additional supervision. It extracts knowledge from self-contained order information of training sequences. Extensive experiments on benchmark datasets demonstrate the effectiveness of leveraging character-level knowledge and the efficiency of co-training. For example, on the CoNLL03 NER task, model training completes in about 6 hours on a single GPU, reaching F1 score of 91.71±0.10 without using any extra annotation.]]></description>
<dc:subject>natural-language-processing deep-learning neural-networks nudge-targets consider:feature-discovery consider:representation to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:6531ca12a758/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1611.05896">
    <title>[1611.05896] Answering Image Riddles using Vision and Reasoning through Probabilistic Soft Logic</title>
    <dc:date>2018-03-10T13:41:36+00:00</dc:date>
    <link>https://arxiv.org/abs/1611.05896</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this work, we explore a genre of puzzles ("image riddles") which involves a set of images and a question. Answering these puzzles require both capabilities involving visual detection (including object, activity recognition) and, knowledge-based or commonsense reasoning. We compile a dataset of over 3k riddles where each riddle consists of 4 images and a groundtruth answer. The annotations are validated using crowd-sourced evaluation. We also define an automatic evaluation metric to track future progress. Our task bears similarity with the commonly known IQ tasks such as analogy solving, sequence filling that are often used to test intelligence. 
We develop a Probabilistic Reasoning-based approach that utilizes probabilistic commonsense knowledge to answer these riddles with a reasonable accuracy. We demonstrate the results of our approach using both automatic and human evaluations. Our approach achieves some promising results for these riddles and provides a strong baseline for future attempts. We make the entire dataset and related materials publicly available to the community in ImageRiddle Website (this http URL).]]></description>
<dc:subject>machine-learning image-processing natural-language-processing deep-learning puzzles rather-interesting to-write-about nudge-targets consider:looking-to-see consider:integrating-NLP</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:c5a993f62ebd/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:puzzles"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:integrating-NLP"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1710.02271">
    <title>[1710.02271] Unsupervised Extraction of Representative Concepts from Scientific Literature</title>
    <dc:date>2018-02-27T12:39:20+00:00</dc:date>
    <link>https://arxiv.org/abs/1710.02271</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This paper studies the automated categorization and extraction of scientific concepts from titles of scientific articles, in order to gain a deeper understanding of their key contributions and facilitate the construction of a generic academic knowledgebase. Towards this goal, we propose an unsupervised, domain-independent, and scalable two-phase algorithm to type and extract key concept mentions into aspects of interest (e.g., Techniques, Applications, etc.). In the first phase of our algorithm we propose PhraseType, a probabilistic generative model which exploits textual features and limited POS tags to broadly segment text snippets into aspect-typed phrases. We extend this model to simultaneously learn aspect-specific features and identify academic domains in multi-domain corpora, since the two tasks mutually enhance each other. In the second phase, we propose an approach based on adaptor grammars to extract fine grained concept mentions from the aspect-typed phrases without the need for any external resources or human effort, in a purely data-driven manner. We apply our technique to study literature from diverse scientific domains and show significant gains over state-of-the-art concept extraction techniques. We also present a qualitative analysis of the results obtained.
]]></description>
<dc:subject>natural-language-processing POS-tagging algorithms data-fusion machine-learning text-mining nudge-targets consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b28387eb58c8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:POS-tagging"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:data-fusion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:text-mining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1703.00607">
    <title>[1703.00607] Dynamic Word Embeddings for Evolving Semantic Discovery</title>
    <dc:date>2018-02-25T12:48:56+00:00</dc:date>
    <link>https://arxiv.org/abs/1703.00607</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Word evolution refers to the changing meanings and associations of words throughout time, as a byproduct of human language evolution. By studying word evolution, we can infer social trends and language constructs over different periods of human history. However, traditional techniques such as word representation learning do not adequately capture the evolving language structure and vocabulary. In this paper, we develop a dynamic statistical model to learn time-aware word vector representation. We propose a model that simultaneously learns time-aware embeddings and solves the resulting "alignment problem". This model is trained on a crawled NYTimes dataset. Additionally, we develop multiple intuitive evaluation strategies of temporal word embeddings. Our qualitative and quantitative tests indicate that our method not only reliably captures this evolution over time, but also consistently outperforms state-of-the-art temporal embedding approaches on both semantic accuracy and alignment quality.
]]></description>
<dc:subject>time-series digital-humanities natural-language-processing representation nudge to-write-about to-do</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b5cbb8b64478/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-do"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://blog.acolyer.org/2018/02/22/dynamic-word-embeddings-for-evolving-semantic-discovery/">
    <title>Dynamic word embeddings for evolving semantic discovery | the morning paper</title>
    <dc:date>2018-02-25T12:48:19+00:00</dc:date>
    <link>https://blog.acolyer.org/2018/02/22/dynamic-word-embeddings-for-evolving-semantic-discovery/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Prior approaches to solving this problem first use independent learning as per our straw man, and then post process the embeddings in an alignment phase to try and match them up. But Yao et al. have found a way to learn temporal embeddings in all time slices concurrently, doing away with the need for a separate alignment phase. The experimental results suggests that this yields better outcomes that the prior two-step methods, and the approach is also robust against data sparsity (it will tolerate time slices where some words are rarely present or even missing).

]]></description>
<dc:subject>digital-humanities time-series rather-interesting to-write-about natural-language-processing representation nudge consider:generalization</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:b88776ab53ba/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:digital-humanities"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:time-series"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:generalization"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1705.08432">
    <title>[1705.08432] Question-Answering with Grammatically-Interpretable Representations</title>
    <dc:date>2018-02-24T12:17:16+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.08432</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We introduce an architecture, the Tensor Product Recurrent Network (TPRN). In our application of TPRN, internal representations learned by end-to-end optimization in a deep neural network performing a textual question-answering (QA) task can be interpreted using basic concepts from linguistic theory. No performance penalty need be paid for this increased interpretability: the proposed model performs comparably to a state-of-the-art system on the SQuAD QA task. The internal representation which is interpreted is a Tensor Product Representation: for each input word, the model selects a symbol to encode the word, and a role in which to place the symbol, and binds the two together. The selection is via soft attention. The overall interpretation is built from interpretations of the symbols, as recruited by the trained model, and interpretations of the roles as used by the model. We find support for our initial hypothesis that symbols can be interpreted as lexical-semantic word meanings, while roles can be interpreted as approximations of grammatical roles (or categories) such as subject, wh-word, determiner, etc. Fine-grained analysis reveals specific correspondences between the learned roles and parts of speech as assigned by a standard tagger (Toutanova et al. 2003), and finds several discrepancies in the model's favor. In this sense, the model learns significant aspects of grammar, after having been exposed solely to linguistically unannotated text, questions, and answers: no prior linguistic knowledge is given to the model. What is given is the means to build representations using symbols and roles, with an inductive bias favoring use of these in an approximately discrete manner.
]]></description>
<dc:subject>natural-language-processing deep-learning recurrent-neural-networks rather-interesting representation to-write-about machine-learning</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a155090f15e1/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:recurrent-neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1709.08878">
    <title>[1709.08878] Generating Sentences by Editing Prototypes</title>
    <dc:date>2018-01-28T12:47:33+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.08878</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[We propose a new generative model of sentences that first samples a prototype sentence from the training corpus and then edits it into a new sentence. Compared to traditional models that generate from scratch either left-to-right or by first sampling a latent sentence vector, our prototype-then-edit model improves perplexity on language modeling and generates higher quality outputs according to human evaluation. Furthermore, the model gives rise to a latent edit vector that captures interpretable semantics such as sentence similarity and sentence-level analogies.
]]></description>
<dc:subject>machine-learning natural-language-processing rather-interesting representation to-write-about nudge-targets consider:representation consider:performance-measures generative-models</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:fec7242f7485/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-models"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1705.00441">
    <title>[1705.00441] Learning Topic-Sensitive Word Representations</title>
    <dc:date>2018-01-26T12:26:19+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.00441</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Distributed word representations are widely used for modeling words in NLP tasks. Most of the existing models generate one representation per word and do not consider different meanings of a word. We present two approaches to learn multiple topic-sensitive representations per word by using Hierarchical Dirichlet Process. We observe that by modeling topics and integrating topic distributions for each document we obtain representations that are able to distinguish between different meanings of a given word. Our models yield statistically significant improvements for the lexical substitution task indicating that commonly used single word representations, even when combined with contextual information, are insufficient for this task.]]></description>
<dc:subject>natural-language-processing feature-construction neural-networks algorithms nudge-targets consider:looking-to-see consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:44d5c2f535e4/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-construction"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/mewo2/ketchum">
    <title>mewo2/ketchum: Use word vectors to interactively generate lists of similar words</title>
    <dc:date>2018-01-15T11:31:39+00:00</dc:date>
    <link>https://github.com/mewo2/ketchum</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This is code for generating lists of similar words, using word vector similarities from the fasttext data, released by Facebook. It's useful for building collections of words to slot into generative grammars, such as Kate Compton's tracery.

]]></description>
<dc:subject>natural-language-processing software library to-understand to-do software-development</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:4d63b4d2acad/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:library"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-understand"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-do"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:software-development"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1710.03370">
    <title>[1710.03370] iVQA: Inverse Visual Question Answering</title>
    <dc:date>2017-11-27T12:25:55+00:00</dc:date>
    <link>https://arxiv.org/abs/1710.03370</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In recent years, visual question answering (VQA) has become topical as a long-term goal to drive computer vision and multi-disciplinary AI research. The premise of VQA's significance, is that both the image and textual question need to be well understood and mutually grounded in order to infer the correct answer. However, current VQA models perhaps `understand' less than initially hoped, and instead master the easier task of exploiting cues given away in the question and biases in the answer distribution. 
In this paper we propose the inverse problem of VQA (iVQA), and explore its suitability as a benchmark for visuo-linguistic understanding. The iVQA task is to generate a question that corresponds to a given image and answer pair. Since the answers are less informative than the questions, and the questions have less learnable bias, an iVQA model needs to better understand the image to be successful. We pose question generation as a multi-modal dynamic inference process and propose an iVQA model that can gradually adjust its focus of attention guided by both a partially generated question and the answer. For evaluation, apart from existing linguistic metrics, we propose a new ranking metric. This metric compares the ground truth question's rank among a list of distractors, which allows the drawbacks of different algorithms and sources of error to be studied. Experimental results show that our model can generate diverse, grammatically correct and content correlated questions that match the given answer.]]></description>
<dc:subject>artificial-intelligence image-analysis rather-interesting jeopardy-questions inverse-problems natural-language-processing to-write-about nudge-targets benchmarks</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a3248633e3a5/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:artificial-intelligence"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:image-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:jeopardy-questions"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:inverse-problems"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:benchmarks"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1707.05589">
    <title>[1707.05589] On the State of the Art of Evaluation in Neural Language Models</title>
    <dc:date>2017-11-12T12:22:50+00:00</dc:date>
    <link>https://arxiv.org/abs/1707.05589</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Ongoing innovations in recurrent neural network architectures have provided a steady influx of apparently state-of-the-art results on language modelling benchmarks. However, these have been evaluated using differing code bases and limited computational resources, which represent uncontrolled sources of experimental variation. We reevaluate several popular architectures and regularisation methods with large-scale automatic black-box hyperparameter tuning and arrive at the somewhat surprising conclusion that standard LSTM architectures, when properly regularised, outperform more recent models. We establish a new state of the art on the Penn Treebank and Wikitext-2 corpora, as well as strong baselines on the Hutter Prize dataset.
]]></description>
<dc:subject>natural-language-processing representation machine-learning deep-learning to-write-about</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:064bbb224ea8/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1706.04902">
    <title>[1706.04902] A Survey Of Cross-lingual Word Embedding Models</title>
    <dc:date>2017-11-03T11:57:17+00:00</dc:date>
    <link>https://arxiv.org/abs/1706.04902</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Cross-lingual representations of words enable us to reason about word meaning in multilingual contexts and are a key facilitator of cross-lingual transfer when developing natural language processing models for low-resource languages. In this survey, we provide a comprehensive typology of cross-lingual word embedding models. We compare their data requirements and objective functions. The recurring theme of the survey is that many of the models presented in the literature optimize for the same objectives, and that seemingly different models are often equivalent modulo optimization strategies, hyper-parameters, and such. We also discuss the different ways cross-lingual word embeddings are evaluated, as well as future challenges and research horizons.]]></description>
<dc:subject>natural-language-processing representation review rather-interesting to-write-about to-do algorithms feature-extraction</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:5b1f6e2d2c8f/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:review"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-do"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:feature-extraction"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.andrewdavidson.com/gibberish/?companyname=Floopr">
    <title>Corporate Gibberish Generator on AndrewDavidson.com</title>
    <dc:date>2017-10-05T10:44:28+00:00</dc:date>
    <link>http://www.andrewdavidson.com/gibberish/?companyname=Floopr</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Welcome to the Corporate Gibberish Generator™ by Andrew Davidson. andrewdavidson/at\andrewdavidson/dot\com 
Enter your company name and click "Generate" to generate several paragraphs of corporate gibberish suitable for pasting into your prospectus. 
(The gibberish is geared more toward Internet and technology companies.)]]></description>
<dc:subject>branding corporatism humor algorithms natural-language-processing generative-art</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ea3bac96cd08/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:branding"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:corporatism"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:humor"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:generative-art"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://blog.openai.com/unsupervised-sentiment-neuron/">
    <title>Unsupervised Sentiment Neuron</title>
    <dc:date>2017-09-30T12:47:47+00:00</dc:date>
    <link>https://blog.openai.com/unsupervised-sentiment-neuron/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[It’s interesting to note that the system also makes large updates after the completion of sentences and phrases. For example, in “And about 99.8 percent of that got lost in the film”, there’s a negative update after “lost” and a larger update at the sentence’s end, even though “in the film” has no sentiment content on its own.

]]></description>
<dc:subject>sentiment-analysis neural-networks machine-learning natural-language-processing rather-interesting to-write-about consider:cause-and-effect consider:feature-discovery</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:9d6253232246/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:sentiment-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:rather-interesting"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:to-write-about"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:cause-and-effect"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:feature-discovery"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1709.06309">
    <title>[1709.06309] Aspect-Based Relational Sentiment Analysis Using a Stacked Neural Network Architecture</title>
    <dc:date>2017-09-29T13:38:27+00:00</dc:date>
    <link>https://arxiv.org/abs/1709.06309</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Sentiment analysis can be regarded as a relation extraction problem in which the sentiment of some opinion holder towards a certain aspect of a product, theme or event needs to be extracted. We present a novel neural architecture for sentiment analysis as a relation extraction problem that addresses this problem by dividing it into three subtasks: i) identification of aspect and opinion terms, ii) labeling of opinion terms with a sentiment, and iii) extraction of relations between opinion terms and aspect terms. For each subtask, we propose a neural network based component and combine all of them into a complete system for relational sentiment analysis. The component for aspect and opinion term extraction is a hybrid architecture consisting of a recurrent neural network stacked on top of a convolutional neural network. This approach outperforms a standard convolutional deep neural architecture as well as a recurrent network architecture and performs competitively compared to other methods on two datasets of annotated customer reviews. To extract sentiments for individual opinion terms, we propose a recurrent architecture in combination with word distance features and achieve promising results, outperforming a majority baseline by 18% accuracy and providing the first results for the USAGE dataset. Our relation extraction component outperforms the current state-of-the-art in aspect-opinion relation extraction by 15% F-Measure.
]]></description>
<dc:subject>sentiment-analysis natural-language-processing deep-learning neural-networks machine-learning architecture nudge-targets consider:representation</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ed09c9f5797d/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:sentiment-analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:architecture"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1705.01991">
    <title>[1705.01991] Sharp Models on Dull Hardware: Fast and Accurate Neural Machine Translation Decoding on the CPU</title>
    <dc:date>2017-09-26T12:42:37+00:00</dc:date>
    <link>https://arxiv.org/abs/1705.01991</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[Attentional sequence-to-sequence models have become the new standard for machine translation, but one challenge of such models is a significant increase in training and decoding cost compared to phrase-based systems. Here, we focus on efficient decoding, with a goal of achieving accuracy close the state-of-the-art in neural machine translation (NMT), while achieving CPU decoding speed/throughput close to that of a phrasal decoder. 
We approach this problem from two angles: First, we describe several techniques for speeding up an NMT beam search decoder, which obtain a 4.4x speedup over a very efficient baseline decoder without changing the decoder output. Second, we propose a simple but powerful network architecture which uses an RNN (GRU/LSTM) layer at bottom, followed by a series of stacked fully-connected layers applied at every timestep. This architecture achieves similar accuracy to a deep recurrent model, at a small fraction of the training and decoding cost. By combining these techniques, our best system achieves a very competitive accuracy of 38.3 BLEU on WMT English-French NewsTest2014, while decoding at 100 words/sec on single-threaded CPU. We believe this is the best published accuracy/speed trade-off of an NMT system.
]]></description>
<dc:subject>machine-learning representation algorithms deep-learning neural-networks approximation nudge-targets consider:performance-measures consider:representation natural-language-processing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:a97c0712a71b/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:machine-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:deep-learning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:neural-networks"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:approximation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://arxiv.org/abs/1608.02025">
    <title>[1608.02025] Boundary-based MWE segmentation with text partitioning</title>
    <dc:date>2017-09-25T20:15:08+00:00</dc:date>
    <link>https://arxiv.org/abs/1608.02025</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[This work presents a fine-grained, text-chunking algorithm designed for the task of multiword expressions (MWEs) segmentation. As a lexical class, MWEs include a wide variety of idioms, whose automatic identification are a necessity for the handling of colloquial language. This algorithm's core novelty is its use of non-word tokens, i.e., boundaries, in a bottom-up strategy. Leveraging boundaries refines token-level information, forging high-level performance from relatively basic data. The generality of this model's feature space allows for its application across languages and domains. Experiments spanning 19 different languages exhibit a broadly-applicable, state-of-the-art model. Evaluation against recent shared-task data places text partitioning as the overall, best performing MWE segmentation algorithm, covering all MWE classes and multiple English domains (including user-generated text). This performance, coupled with a non-combinatorial, fast-running design, produces an ideal combination for implementations at scale, which are facilitated through the release of open-source software.
]]></description>
<dc:subject>natural-language-processing algorithms parsing nudge-targets consider:looking-to-see consider:representation consider:performance-measures</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:ac70ad8a04b9/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:algorithms"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:parsing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:nudge-targets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:looking-to-see"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:representation"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:consider:performance-measures"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://jasmcole.com/2017/06/04/swype-right/">
    <title>Swype right – Almost looks like work</title>
    <dc:date>2017-08-12T12:46:39+00:00</dc:date>
    <link>https://jasmcole.com/2017/06/04/swype-right/</link>
    <dc:creator>Vaguery</dc:creator><description><![CDATA[In this post I’ll discuss optimising the layout of an English QWERTY keyboard in an effort to minimise the average distance a digit must travel to type a word. Let’s have a look.

]]></description>
<dc:subject>mathematical-recreations optimization natural-language-processing user-interface amusing</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:Vaguery/b:2ba5576a2eed/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:mathematical-recreations"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:optimization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:natural-language-processing"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:user-interface"/>
	<rdf:li rdf:resource="https://pinboard.in/u:Vaguery/t:amusing"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>