Pinboard (johnpaulett)
https://pinboard.in/u:johnpaulett/public/
recent bookmarks from johnpaulettgoogle/langextract: A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.2025-07-31T00:55:57+00:00
https://github.com/google/langextract
johnpaulettml nlphttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:e6bc72405d53/Radiology Report Structuring2025-07-31T00:53:06+00:00
https://google-radextract.hf.space/
johnpaulettradiology huggingface ml nlphttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:7a20394af759/Unlocking Healthcare AI: I'm Releasing State-of-the-Art Medical Models for Free. Forever.2025-07-17T12:56:40+00:00
https://huggingface.co/blog/MaziyarPanahi/open-health-ai
johnpaulettner nlp healthcare huggingfacehttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:85d0f82c4505/chandar-lab/NeoBERT · Hugging Face2025-03-03T15:23:01+00:00
https://huggingface.co/chandar-lab/NeoBERT
johnpaulettbert nlp ai encoderhttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:3a8fa4fb7f10/A Simple Algorithm for Identifying Negated Findings and Diseases in Discharge Summaries - ScienceDirect2025-02-18T15:01:59+00:00
https://www.sciencedirect.com/science/article/pii/S1532046401910299?via%3Dihub
johnpaulettnegex nlphttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:f81c37859df6/GitHub - explosion/spacy-llm: 🦙 Integrating LLMs into structured NLP pipelines2025-01-10T13:03:38+00:00
https://github.com/explosion/spacy-llm
johnpaulettspacy nlp huggingface llmhttps://pinboard.in/u:johnpaulett/b:7889b24b8d83/Finally, a Replacement for BERT: Introducing ModernBERT2024-12-20T00:49:32+00:00
https://huggingface.co/blog/modernbert
johnpaulettBERT embeddings NLPhttps://pinboard.in/u:johnpaulett/b:73a73b8f3783/RedPajama-Data-v2: an Open Dataset with 30 Trillion Tokens for Training Large Language Models — Together AI2023-10-31T09:06:28+00:00
https://together.ai/blog/redpajama-data-v2
johnpaulettnlp llm datasetshttps://pinboard.in/u:johnpaulett/b:67df62f4a687/StanfordAIMI/stanford-deidentifier-base · Hugging Face2023-03-12T17:45:41+00:00
https://huggingface.co/StanfordAIMI/stanford-deidentifier-base
johnpaulettnlp radiologyhttps://pinboard.in/u:johnpaulett/b:e7955c0e9c7d/GitHub - ggerganov/llama.cpp: Port of Facebook's LLaMA model in C/C++2023-03-12T14:45:07+00:00
https://github.com/ggerganov/llama.cpp
johnpaulettllm nlp chatgpt applesilicon arm64 aihttps://pinboard.in/u:johnpaulett/b:f4b88bb32f7c/Transcribed Medical Transcription Sample Reports and Examples - MTSamples2023-02-28T22:36:01+00:00
https://www.mtsamples.com/
johnpaulettnlp radiologyhttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:1c7daa1c19ea/SMMRY - About2023-01-27T12:56:08+00:00
https://smmry.com/about
johnpaulettnlp summarizationhttps://pinboard.in/u:johnpaulett/b:9cb48150fc78/Med7 — an information extraction model for clinical natural language processing | by kormilitzin | Medium2021-03-17T01:34:53+00:00
https://medium.com/@kormilitzin/med7-clinical-information-extraction-system-in-python-and-spacy-5e6f68ab1c68
johnpauletthealthit scapy python nlphttps://pinboard.in/u:johnpaulett/b:559572f0ea3b/huggingface/transformers: 🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.2021-02-19T13:07:51+00:00
https://github.com/huggingface/transformers
johnpaulettai nlp python pytorch berthttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:03bbcaf606bc/Recent advances in Natural Language Processing- Some Woolly speculations – DePonySum2020-08-16T19:31:04+00:00
https://deponysum.com/2020/01/16/recent-advances-in-natural-language-processing-some-woolly-speculations/
johnpaulettnlphttps://pinboard.in/u:johnpaulett/b:adc934f687b2/How to Tokenize Japanese in Python2020-08-14T23:45:46+00:00
https://www.dampfkraft.com/nlp/how-to-tokenize-japanese.html
johnpaulettnlp Japanese pythonhttps://pinboard.in/u:johnpaulett/b:85f2603a8fa6/GPT-3 Creative Fiction · Gwern.net2020-07-04T00:45:13+00:00
https://www.gwern.net/GPT-3
johnpaulettnlp ai ml gpt-3https://pinboard.in/u:johnpaulett/b:57adb3f3f896/KoNLPy: Korean NLP in Python — KoNLPy 0.5.2 documentation2020-07-01T21:47:30+00:00
http://konlpy.org/en/latest/
johnpaulettnlp korea pythonhttps://pinboard.in/u:johnpaulett/b:2f942650158b/PKSHATechnology-Research/camphr: spaCy plugin for Transformers , Udify, ELmo, etc.2020-02-13T14:42:36+00:00
https://github.com/PKSHATechnology-Research/camphr
johnpaulettnlp spacy pythonhttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:0f9c3ca7eea8/Google AI Blog: ALBERT: A Lite BERT for Self-Supervised Learning of Language Representations2020-01-08T14:49:10+00:00
https://ai.googleblog.com/2019/12/albert-lite-bert-for-self-supervised.html
johnpaulettdeeplearning bert nlp mlhttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:5fc2df0c3b7a/Netanos2020-01-06T15:48:09+00:00
http://netanos.io/
johnpaulettanonymization nlphttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:72df92d39b9f/microsoft/presidio: Context aware, pluggable and customizable data protection and anonymization service for text and images2020-01-06T15:47:58+00:00
https://github.com/Microsoft/presidio
johnpaulettanonymization text nlphttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:dcf803d0a7cf/How University of Rochester uses AI to reduce risk of failed follow-up | Healthcare IT News2019-08-28T10:33:37+00:00
https://www.healthcareitnews.com/news/how-university-rochester-uses-ai-reduce-risk-failed-follow
johnpaulettmontage nlphttps://pinboard.in/u:johnpaulett/b:d897f4369c7c/OpenGPT-2: We Replicated GPT-2 Because You Can Too - Vanya Cohen - Medium2019-08-23T20:24:51+00:00
https://medium.com/@vanya_cohen/opengpt-2-we-replicated-gpt-2-because-you-can-too-45e34e6d36dc
johnpaulettai nlp deeplearninghttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:bf715057f56b/EmilyAlsentzer/clinicalBERT: repository for Publicly Available Clinical BERT Embeddings2019-06-27T18:04:29+00:00
https://github.com/EmilyAlsentzer/clinicalBERT
johnpaulettbert nlp aihttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:7b21e6b4222c/The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning) – Jay Alammar – Visualizing machine learning one concept at a time2019-06-26T22:37:06+00:00
https://jalammar.github.io/illustrated-bert/
johnpaulettnlp deeplearning aihttps://pinboard.in/u:johnpaulett/b:b1d5e7c27237/openai/gpt-2: Code for the paper "Language Models are Unsupervised Multitask Learners"2019-04-22T12:02:19+00:00
https://github.com/openai/gpt-2
johnpaulettai nlp machine-learning texthttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:79c672d42519/Evaluating Text Output in NLP: BLEU at your own risk2019-01-26T14:35:03+00:00
https://towardsdatascience.com/evaluating-text-output-in-nlp-bleu-at-your-own-risk-e8609665a213
johnpaulettnlp ai machinelearninghttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:83d15d1062d4/What Kagglers are using for Text Classification2018-12-28T03:03:55+00:00
https://mlwhiz.com/blog/2018/12/17/text_classification/
johnpaulettclassification DeepLearning nlp lstmhttps://pinboard.in/u:johnpaulett/b:b65e16b2737e/facebookresearch/pytext: A natural language modeling framework based on PyTorch2018-12-14T21:45:06+00:00
https://github.com/facebookresearch/PyText
johnpaulettpytorch nlp machinelearninghttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:931f4cf2cd4c/gensim: Topic modelling for humans2018-08-29T18:09:56+00:00
https://radimrehurek.com/gensim/
johnpaulettmachinelearning nlp aihttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:4e043f777a90/Dataturks – ML data annotations and labeling doesn't need to suck2018-04-18T20:18:27+00:00
https://dataturks.com/
johnpaulettnlp ml labeling trainging datasetshttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:7a0214c47c98/Universal Sentence Encoder by Ray Kurzweil's Team at Google | Hacker News2018-03-30T16:33:53+00:00
https://news.ycombinator.com/item?id=16713964
johnpaulettml nlp word2vechttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:e40b55d153eb/GitHub - marcotcr/lime: Lime: Explaining the predictions of any machine learning classifier2018-02-06T11:17:07+00:00
https://github.com/marcotcr/lime
johnpaulettmachinelearning ml nlp machine-learninghttps://pinboard.in/u:johnpaulett/b:997eff4a4cda/AllenNLP2017-09-12T21:19:38+00:00
http://allennlp.org/
johnpaulettnlp deeplearning machinelearninghttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:5f4f3614b53d/astorfi/speechpy: SpeechPy - A Library for Speech Processing and Recognition2017-09-07T20:10:19+00:00
https://github.com/astorfi/speechpy
johnpaulettnlp speech-recognition speech pythonhttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:442820bf45de/Exploring LSTMs2017-06-10T11:26:27+00:00
http://blog.echen.me/2017/05/30/exploring-lstms/
johnpaulettLSTM ml deeplearning nlphttps://pinboard.in/u:johnpaulett/b:467e24fba63d/spaCy - Industrial-strength Natural Language Processing in Python2017-03-16T16:53:01+00:00
https://spacy.io/
johnpaulettnlp pythonhttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:003ff12a5cf8/A tale about LDA2vec: when LDA meets word2vec - Data Science Central2016-12-18T00:59:41+00:00
http://www.datasciencecentral.com/profiles/blogs/a-tale-about-lda2vec-when-lda-meets-word2vec
johnpaulettnlp cnn word2vec lda summarizerhttps://pinboard.in/u:johnpaulett/b:a955d75f30d9/Wired Informatics | Next Generation NLP Platform2016-12-02T00:57:50+00:00
http://www.wiredinformatics.com/
johnpaulettcytpes nlp healthit informaticshttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:44a4f623bf3f/A Natural Language Query Engine without Machine Learning – ayoungprogrammer's blog2016-10-08T17:03:56+00:00
http://blog.ayoungprogrammer.com/2016/10/natural-lang-query-engine.html/
johnpaulettnlphttps://pinboard.in/u:johnpaulett/b:372c6c0465b2/Markov chain - Wikipedia, the free encyclopedia2016-09-06T12:26:02+00:00
https://en.wikipedia.org/wiki/Markov_chain#Markov_text_generators
johnpaulettnlp ai ideashttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:9ff923cee789/facebookresearch/fastText: Library for fast text representation and classification.2016-08-19T20:08:27+00:00
https://github.com/facebookresearch/fastText
johnpaulettnlp classificationhttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:960dea5ede5f/LexVec, a word embedding model written in Go that outperforms word2vec | Hacker News2016-07-27T22:15:18+00:00
https://news.ycombinator.com/item?id=12172008
johnpaulettnlp parsing neural-networks word2vec golanghttps://pinboard.in/u:johnpaulett/b:3f62ee5555a6/Introducing DeepText: Facebook's text understanding engine | Engineering Blog | Facebook Code | Facebook2016-06-03T12:37:10+00:00
https://code.facebook.com/posts/181565595577955/introducing-deeptext-facebook-s-text-understanding-engine/
johnpaulettnlp ai tensorflow deeplearninghttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:b402ca1e123e/Research Blog: Announcing SyntaxNet: The World’s Most Accurate Parser Goes Open Source2016-05-13T09:45:08+00:00
http://googleresearch.blogspot.com/2016/05/announcing-syntaxnet-worlds-most.html?m=1
johnpaulettnlp google ai nlu tensorflow deeplearninghttps://pinboard.in/u:johnpaulett/b:7d72bb45166d/Implementing a CNN for Text Classification in TensorFlow – WildML2015-12-13T01:44:58+00:00
http://www.wildml.com/2015/12/implementing-a-cnn-for-text-classification-in-tensorflow/
johnpaulettml tensorflow cnn machinelearning nlphttps://pinboard.in/u:johnpaulett/b:52e6b75166f5/DL4NLP/README.md at master · andrewt3000/DL4NLP2015-10-28T11:52:11+00:00
https://github.com/andrewt3000/DL4NLP/blob/master/README.md#deep-learning-for-nlp-resources
johnpaulettnlp machinelearning neuralnetwork ai deeplearninghttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:0effacb0647c/spaCy.io | Build Tomorrow's Language Technologies2015-09-08T13:50:24+00:00
http://spacy.io/
johnpaulettnlp python nltkhttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:7f483e59b973/wordfreq: Open source and open data about word frequencies | Luminoso Blog2015-09-02T10:55:13+00:00
http://blog.luminoso.com/2015/09/01/wordfreq-open-source-and-open-data-about-word-frequencies/
johnpaulettnlphttps://pinboard.in/u:johnpaulett/b:87792e79fc88/Durat.io2015-07-13T19:56:20+00:00
http://durat.io/
johnpauletttime datetime nlp iso8601https://pinboard.in/https://pinboard.in/u:johnpaulett/b:3cd8da5a3c42/Durat.io2015-07-13T19:56:11+00:00
http://durat.io/?q=08%3a00+until+16%3a30+-+1+hour+-+15+minutes&%3f=
johnpauletttime datetime nlp iso8601https://pinboard.in/https://pinboard.in/u:johnpaulett/b:ee28a9570c66/Working With Text Data — scikit-learn 0.16.1 documentation2015-06-05T10:00:43+00:00
http://scikit-learn.org/stable/tutorial/text_analytics/working_with_text_data.html
johnpaulettscikit nlp machinelearning texthttps://pinboard.in/u:johnpaulett/b:08df216aef34/spaCy: Industrial-strength NLP — spaCy 1.0 documentation2015-01-25T14:13:35+00:00
http://honnibal.github.io/spaCy/
johnpaulettpython nlp nltkhttps://pinboard.in/u:johnpaulett/b:c9bd06a8eebc/What Happened to Old School NLP? | Hacker News2015-01-12T12:17:52+00:00
https://news.ycombinator.com/item?id=8872588
johnpaulettnlp hackernewshttps://pinboard.in/u:johnpaulett/b:edc31310f48f/Flipboard's summarization algorithm, sort of2015-01-01T12:12:41+00:00
https://gist.github.com/rodricios/fee45381356c8fb36004
johnpaulettnlp summarization pythonhttps://pinboard.in/u:johnpaulett/b:8dcb275a458b/Flipboard's Approach to Automatic Summarization — Flipboard Engineering2015-01-01T12:12:10+00:00
http://engineering.flipboard.com/2014/10/summarization/
johnpaulettnlp summarization machinelearninghttps://pinboard.in/u:johnpaulett/b:43886a724499/Duckling2014-10-01T18:02:58+00:00
http://duckling-lib.org/
johnpaulettclojure nlp datetimehttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:806d110d6816/Extract text from any document; no muss, no fuss. | DsA2014-08-13T16:41:30+00:00
http://datascopeanalytics.com/what-we-think/2014/07/27/extract-text-from-any-document-no-muss-no-fuss
johnpaulettnlp python text doc pdfhttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:bb76c512c893/etcML - Home2014-02-07T14:22:42+00:00
http://www.etcml.com/
johnpaulettnlp classification text api analysishttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:eb6716eb611b/The Stanford NLP (Natural Language Processing) Group2014-01-05T13:19:39+00:00
http://nlp.stanford.edu/projects/arabic.shtml
johnpaulettArabic nlphttps://pinboard.in/u:johnpaulett/b:89e9468ebc37/pygram/pygram2013-12-16T13:52:58+00:00
https://github.com/pygram/pygram
johnpaulettparser python ply grammar nlphttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:b4290c33ab1a/Stanford researchers to open-source model they say has nailed sentiment analysis — Tech News and Analysis2013-10-04T20:19:32+00:00
http://gigaom.com/2013/10/03/stanford-researchers-to-open-source-model-they-say-has-nailed-sentiment-analysis/
johnpaulettai analysis nlp languagehttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:b9ea12e370f5/ATodd – When Harvard Met Sally: N-gram Analysis of the New York Times Weddings Section | News Genius2013-09-04T18:45:59+00:00
http://news.rapgenius.com/Atodd-when-harvard-met-sally-n-gram-analysis-of-the-new-york-times-weddings-section-lyrics
johnpaulettnytimes ngram nlphttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:0a08f089cef7/TextBlob: Simplified Text Processing — TextBlob 0.5.0 documentation2013-08-11T13:14:53+00:00
https://textblob.readthedocs.org/en/latest/
johnpaulettnltk nlp pythonhttps://pinboard.in/u:johnpaulett/b:a2c03a2f3e0c/clips/pattern · GitHub2012-10-14T14:54:02+00:00
https://github.com/clips/pattern
johnpaulettpython nlp scrapinghttps://pinboard.in/u:johnpaulett/b:925d2d379a9c/Elegant exact string match using BWT | Read Through Transcription2012-04-24T11:10:51+00:00
http://blog.avadis-ngs.com/2012/04/elegant-exact-string-match-using-bwt-2/
johnpaulettbwt nlp algorithmshttps://pinboard.in/u:johnpaulett/b:4ae1dc4353b2/Twitter sentiment analysis using Python and NLTK | Laurent Luce's Blog2012-03-15T14:41:22+00:00
http://www.laurentluce.com/posts/twitter-sentiment-analysis-using-python-and-nltk/
johnpaulettnltk python twitter nlp sentimentanalysishttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:370d40b2e833/LingPipe: Signicant Phrases Tutorial2012-01-31T21:22:24+00:00
http://alias-i.com/lingpipe/demos/tutorial/interestingPhrases/read-me.html
johnpaulettamazon datamining nlp nltkhttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:13f0f40a4215/PostgreSQL 9.1 Trigrams teaching LIKE and ILIKE new tricks - Postgres OnLine Journal2011-06-07T12:45:39+00:00
http://www.postgresonline.com/journal/archives/212-PostgreSQL-9.1-Trigrams-teaching-LIKE-and-ILIKE-new-tricks.html
johnpaulettpostgresql trigrams nlphttps://pinboard.in/https://pinboard.in/u:johnpaulett/b:6e54a37d0827/