bheinzerling/bpemb

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

embeddingsmultilingualnatural-language-processingnlpsubword-embeddings

License & maintenance

MIT is a permissive license: free to use commercially with attribution.

Last code push 2 years ago.

	Repository	Stars	Language	License	Activity
1	google-research/bertTensorFlow code and pre-trained models for BERT	★ 40k	Python	Apache-2.0	Archived
2	hankcs/HanLPNatural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Depend	★ 36.5k	Python	Apache-2.0	Active
3	NandhaKishorM/layaNon-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ langua	★ 33.4k	Python	Apache-2.0	Active
4	dair-ai/ML-YouTube-Courses📺 Discover the latest machine learning / AI courses on YouTube.	★ 17.4k	—	CC0-1.0	Stale
5	piskvorky/gensimTopic Modelling for Humans	★ 16.5k	Python	LGPL-2.1	Slowing
6	oxford-cs-deepnlp-2017/lectures Oxford Deep NLP 2017 course	★ 15.9k	—	—	Stale
7	nltk/nltkNLTK Source	★ 14.7k	Python	Apache-2.0	Active
8	flairNLP/flairA very simple framework for state-of-the-art Natural Language Processing (NLP)	★ 14.4k	Python	Other	Slowing