<?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 (msszczep)</title>
    <link>https://pinboard.in/u:msszczep/public/</link>
    <description>recent bookmarks from msszczep</description>
    <items>
      <rdf:Seq>	<rdf:li rdf:resource="https://www.kaggle.com/datasets/abhinavwalia95/entity-annotated-corpus"/>
	<rdf:li rdf:resource="https://framenet.icsi.berkeley.edu/fndrupal/"/>
	<rdf:li rdf:resource="https://github.com/philipperemy/tensorflow-1.4-billion-password-analysis"/>
	<rdf:li rdf:resource="http://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.htm"/>
	<rdf:li rdf:resource="http://mpqa.cs.pitt.edu/"/>
	<rdf:li rdf:resource="https://github.com/dariusk/corpora"/>
	<rdf:li rdf:resource="http://googleresearch.blogspot.com/2014/08/teaching-machines-to-read-between-lines.html"/>
	<rdf:li rdf:resource="https://bitbucket.org/c-w/gutenberg"/>
	<rdf:li rdf:resource="http://www.prooffreader.com/2014/05/graphing-distribution-of-english.html"/>
	<rdf:li rdf:resource="http://norvig.com/ngrams/ch14.pdf"/>
	<rdf:li rdf:resource="http://norvig.com/ngrams/"/>
	<rdf:li rdf:resource="http://blog.useost.com/2012/12/30/valett/"/>
	<rdf:li rdf:resource="http://corpus.byu.edu/coca/"/>
	<rdf:li rdf:resource="http://sunlightfoundation.com/blog/2011/12/12/announcing-the-return-of-capitol-words/"/>
      </rdf:Seq>
    </items>
  </channel><item rdf:about="https://www.kaggle.com/datasets/abhinavwalia95/entity-annotated-corpus">
    <title>Annotated Corpus for Named Entity Recognition</title>
    <dc:date>2023-10-02T19:03:55+00:00</dc:date>
    <link>https://www.kaggle.com/datasets/abhinavwalia95/entity-annotated-corpus</link>
    <dc:creator>msszczep</dc:creator><description><![CDATA[Context:
Annotated Corpus for Named Entity Recognition using GMB(Groningen Meaning Bank) corpus for entity classification with enhanced and popular features by Natural Language Processing applied to the data set.

Tip: Use Pandas Dataframe to load dataset if using Python for convenience.

Content:
This is the extract from GMB corpus which is tagged, annotated and built specifically to train the classifier to predict named entities such as name, location, etc.

]]></description>
<dc:subject>nlp software data bigdata useful programming code corpora</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:675e5db86e7e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:bigdata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:useful"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:code"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://framenet.icsi.berkeley.edu/fndrupal/">
    <title>Welcome to FrameNet! | fndrupal</title>
    <dc:date>2018-01-15T18:58:28+00:00</dc:date>
    <link>https://framenet.icsi.berkeley.edu/fndrupal/</link>
    <dc:creator>msszczep</dc:creator><description><![CDATA[FrameNet maps meaning to form in contemporary English through the theory of Frame Semantics.]]></description>
<dc:subject>linguistics data nlp research semantics semantic word words english reference corpora</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:3a0362b8751e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:linguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:research"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:semantics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:semantic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:word"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:words"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:english"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:reference"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/philipperemy/tensorflow-1.4-billion-password-analysis">
    <title>philipperemy/tensorflow-1.4-billion-password-analysis: Deep Learning model to analyze a large corpus of clear text passwords.</title>
    <dc:date>2017-12-22T15:37:42+00:00</dc:date>
    <link>https://github.com/philipperemy/tensorflow-1.4-billion-password-analysis</link>
    <dc:creator>msszczep</dc:creator><description><![CDATA[Deep Learning model to analyze a large corpus of clear text passwords.
]]></description>
<dc:subject>deeplearning machinelearning nlp text password python corpora data bigdata code software programming github</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:770f92a194ca/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:deeplearning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:machinelearning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:text"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:password"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:bigdata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:code"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:github"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.htm">
    <title>NRC Emotion Lexicon</title>
    <dc:date>2016-09-18T22:49:30+00:00</dc:date>
    <link>http://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.htm</link>
    <dc:creator>msszczep</dc:creator><description><![CDATA[The NRC Emotion Lexicon is a list of English words and their associations with eight basic emotions (anger, fear, anticipation, trust, surprise, sadness, joy, and disgust) and two sentiments (negative and positive). The annotations were manually done by crowdsourcing. ]]></description>
<dc:subject>emotion sentiment analysis data language nlp psychology word words linguistics database corpora</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:bc38abda3bfc/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:emotion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:sentiment"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:psychology"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:word"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:words"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:linguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://mpqa.cs.pitt.edu/">
    <title>MPQA Resources</title>
    <dc:date>2015-11-11T23:55:12+00:00</dc:date>
    <link>http://mpqa.cs.pitt.edu/</link>
    <dc:creator>msszczep</dc:creator><description><![CDATA[The MPQA Opinion Corpus contains news articles from a wide variety of news sources manually annotated for opinions and other private states (i.e., beliefs, emotions, sentiments, speculations, etc.).]]></description>
<dc:subject>nlp opinion corpora bigdata datamining datascience analysis code software programming data text</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:8bed27138946/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:opinion"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:bigdata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:datascience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:analysis"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:code"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:text"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://github.com/dariusk/corpora">
    <title>dariusk/corpora</title>
    <dc:date>2015-09-14T15:12:23+00:00</dc:date>
    <link>https://github.com/dariusk/corpora</link>
    <dc:creator>msszczep</dc:creator><description><![CDATA[corpora is a Github repository containing machine-readable lists of interesting words and phrases that "are potentially useful in the creation of weird internet stuff." The corpora range from the mundane (common English words, animals, corporations, pizza toppings) to the obscure (types of knot, wrestling moves, Lovecraftian deities) to the absurd (states of drunkenness, deceased Spinal Tap drummers, unrhymable words).]]></description>
<dc:subject>data github json text bigdata datascience datasets corpora</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:d5307fe95323/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:github"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:json"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:text"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:bigdata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:datascience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:datasets"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://googleresearch.blogspot.com/2014/08/teaching-machines-to-read-between-lines.html">
    <title>Teaching machines to read between the lines (and a new corpus with entity salience annotations) | Research Blog</title>
    <dc:date>2014-08-28T18:05:49+00:00</dc:date>
    <link>http://googleresearch.blogspot.com/2014/08/teaching-machines-to-read-between-lines.html</link>
    <dc:creator>msszczep</dc:creator><description><![CDATA[To encourage research on leveraging background information, we are releasing a large dataset of annotations to accompany the New York Times Annotated Corpus, including resolved Freebase entity IDs and labels indicating which entities are salient. The salience annotations are determined by automatically aligning entities in the document with entities in accompanying human-written abstracts. Details of the salience annotations and some baseline results are described in our recent paper: A New Entity Salience Task with Millions of Training Examples (Jesse Dunietz and Dan Gillick).

Since our entity resolver works better for named entities like WNBA than for nominals like “coach” (this is the notoriously difficult word sense disambiguation problem, which we’ve previously touched on), the annotations are limited to names. ]]></description>
<dc:subject>ai nlp google code machinelearning corpora data database</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:e414eb1c3f82/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:google"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:code"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:machinelearning"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:database"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="https://bitbucket.org/c-w/gutenberg">
    <title>c-w / Gutenberg — Bitbucket</title>
    <dc:date>2014-08-04T04:28:32+00:00</dc:date>
    <link>https://bitbucket.org/c-w/gutenberg</link>
    <dc:creator>msszczep</dc:creator><description><![CDATA[This package contains a variety of scripts to make working with the Project Gutenberg body of public domain texts easier.]]></description>
<dc:subject>code app api data language words word text corpora python software programming</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:9e30dec7f63e/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:code"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:app"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:api"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:words"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:word"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:text"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:software"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:programming"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://www.prooffreader.com/2014/05/graphing-distribution-of-english.html">
    <title>Graphing the distribution of English letters towards the beginning, middle or end of words - Prooffreader</title>
    <dc:date>2014-06-02T13:13:14+00:00</dc:date>
    <link>http://www.prooffreader.com/2014/05/graphing-distribution-of-english.html</link>
    <dc:creator>msszczep</dc:creator><dc:subject>language alphabet statistics corpora data word words letters english visualization infographic infographics</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:d25f46e482ac/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:alphabet"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:word"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:words"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:letters"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:english"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:visualization"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:infographic"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:infographics"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://norvig.com/ngrams/ch14.pdf">
    <title>Natural Language Corpus Data</title>
    <dc:date>2013-12-24T14:42:57+00:00</dc:date>
    <link>http://norvig.com/ngrams/ch14.pdf</link>
    <dc:creator>msszczep</dc:creator><dc:subject>language linguistics code nlp programming python corpora corpus data bigdata datascience words word</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:95863a13eaf2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:linguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:code"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:programming"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpus"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:bigdata"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:datascience"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:words"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:word"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://norvig.com/ngrams/">
    <title>Natural Language Corpus Data: Beautiful Data</title>
    <dc:date>2013-04-18T18:55:10+00:00</dc:date>
    <link>http://norvig.com/ngrams/</link>
    <dc:creator>msszczep</dc:creator><dc:subject>language nlp data ai python scrabble corpora</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:749160827fe2/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:nlp"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:ai"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:python"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:scrabble"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://blog.useost.com/2012/12/30/valett/">
    <title>Ost — Rethinking the value of Scrabble tiles</title>
    <dc:date>2013-01-02T22:27:16+00:00</dc:date>
    <link>http://blog.useost.com/2012/12/30/valett/</link>
    <dc:creator>msszczep</dc:creator><dc:subject>statistics games english github scrabble corpus language words fun corpora data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:a612747355fe/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:statistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:games"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:english"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:github"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:scrabble"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpus"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:words"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:fun"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://corpus.byu.edu/coca/">
    <title>Corpus of Contemporary American English (COCA)</title>
    <dc:date>2012-05-23T13:35:32+00:00</dc:date>
    <link>http://corpus.byu.edu/coca/</link>
    <dc:creator>msszczep</dc:creator><dc:subject>dictionary english language linguistics corpus corpora data bigdata</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:75201a8365da/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:dictionary"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:english"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:linguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpus"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:bigdata"/>
</rdf:Bag></taxo:topics>
</item>
<item rdf:about="http://sunlightfoundation.com/blog/2011/12/12/announcing-the-return-of-capitol-words/">
    <title>Announcing the Return of &quot;Capitol Words&quot; - Sunlight Foundation</title>
    <dc:date>2012-02-01T03:16:38+00:00</dc:date>
    <link>http://sunlightfoundation.com/blog/2011/12/12/announcing-the-return-of-capitol-words/</link>
    <dc:creator>msszczep</dc:creator><dc:subject>computer linguistics government records politics language words corpora database datamining data</dc:subject>
<dc:source>https://pinboard.in/</dc:source>
<dc:identifier>https://pinboard.in/u:msszczep/b:ff2aa5ea24aa/</dc:identifier>
<taxo:topics><rdf:Bag>	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:computer"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:linguistics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:government"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:records"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:politics"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:language"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:words"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:corpora"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:database"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:datamining"/>
	<rdf:li rdf:resource="https://pinboard.in/u:msszczep/t:data"/>
</rdf:Bag></taxo:topics>
</item>
</rdf:RDF>