Research Lead @earthspecies working on decoding non-human communication with AI/ML. Ex @duolingo. Author of Real-World Natural Language Processing
100-nlp-papers. 100 Must-Read NLP Papers
3.8kgithub-typo-corpus. GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors
521realworldnlp. Example code for "Real-World Natural Language Processing"
342xfspell. xfspell — the Transformer Spell Checker
189nanigonet. NanigoNet — Language detector for code-mixed input supporting 150+19 human+programming languages using deep neural networks
71recto. HTML
48cc-kedict. cc-kedict: Creative Commons Korean-English Dictionary
45zmifanva. zmifanva - Lojban ↔ English Machine Translation Engine
39nltk. NKTL Japanese related files
23camxes.js. Lojban Parser written in JavaScript. Based on camxes.
18cll-ja. Japanese summary translation of "The Complete Lojban Language"
15enja.kdict.org. The world's fastest online dictionary
15paper-reviews.
12awesome-japanese-nlp. 📖 A curated list of resources for Japanese Natural Language Processing (NLP)
9deep-knowledge-tracing. Source code and data sets for Going Deeper with Deep Knowledge Tracing (EDM-2016)
8nlproc-cookbook. Python
7chinese-nlp. mhagiwara's Chinese (language) related files
4universalscripts. Parametrized Universal Scripts—generation model trained from all the scripts in the world
3deepnlp-kata. Deep NLP Kata - Practice Exercises for Deep Learning and Natural Language Processing
3mhagiwara.github.io. Masato Hagiwara's user pages
3englishforhackers.com. HTML
2LojbanDictionary. Swift
2runway-e2e-tts. Real-time text-to-speech using ParallelWaveGAN
2runway-distilgpt. DistilGPT2 model for Runway ML
2www.realworldnlpbook.com. HTML
1nes-music-with-transformer. CSS
1szdict. Creative Commons Chinese-English Dictionary of Tech Terms
1aiml-dict-ja. AIML-dict-ja ― オープンソースの AI (人工知能)・ML (機械学習) 用語辞典
1www.aimlbooks.com. HTML
1fcg.sharedtask.org. Feedback Comment Generation Shared Task
1sotalingua. Python
1biology-study-notes.
1