Pinned Repositories
biblionotes
Quick-and-dirty annotated bibliography generator
dotfiles
Some dotfiles
lijspell
Ligurian spellchecking
sgns-embeddings
NLP word and phrase embeddings, computed via skip-gram with negative sampling
jeanm's Repositories
jeanm/biblionotes
Quick-and-dirty annotated bibliography generator
jeanm/dotfiles
Some dotfiles
jeanm/lijspell
Ligurian spellchecking
jeanm/sgns-embeddings
NLP word and phrase embeddings, computed via skip-gram with negative sampling
jeanm/bib-parser
.bib file parser (BibTeX, BibLaTeX)
jeanm/calamari
OCR Engine based on OCRopy and Kraken
jeanm/cldr
The new home of the Unicode Common Locale Data Repository
jeanm/docs
Universal Dependencies online documentation
jeanm/DPR
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
jeanm/epitran
A tool for transcribing orthographic text as IPA (International Phonetic Alphabet)
jeanm/fairseq
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
jeanm/flores
Facebook Low Resource (FLoRes) MT Benchmark
jeanm/jeanm.github.io
jeanm/KILT
Library for Knowledge Intensive Language Tasks
jeanm/mkweb
Minimal static website generator
jeanm/mtdata
A tool that locates, downloads, and extracts machine translation corpora
jeanm/nlip
NLIP python package
jeanm/pytext-1
A natural language modeling framework based on PyTorch
jeanm/relpron
Code for the article: Laura Rimell, Jean Maillard, Tamara Polajnar and Stephen Clark. 2016. RELPRON: A Relative Clause Composition Data Set for Compositional Distributional Semantics. Computational Linguistics.
jeanm/spaCy
💫 Industrial-strength Natural Language Processing (NLP) in Python
jeanm/stanza
Official Stanford NLP Python Library for Many Human Languages
jeanm/strmapped_enum
jeanm/submitit
Python 3.6+ toolbox for submitting jobs to Slurm
jeanm/text
Data loaders and abstractions for text and NLP
jeanm/translate
Translate - a PyTorch Language Library
jeanm/url-nlp
jeanm/web-languages
Crowd-sourced lists of urls to help Common Crawl crawl under-resourced languages. See https://github.com/commoncrawl/web-languages-code/ for the code