You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Many NLP libraries exist today that support many NLP related tasks. Unfortunately not all of them support more beyond English and few other languages. My GUESS here is Gensim does support more languages. But Does it?
It would be nice if anywhere in the docs it would be specified that Gensim supports languages X.Y.Z (supports Unicode, has language models, ...) - or even better - language agnostic.
Reproduce
A usual search would be "gensim supported languages".
Versions
<= 3.8.3
The text was updated successfully, but these errors were encountered:
Yeah Gensim is language agnostic. It relies on distributional semantics (word co-occurrences) to do unsupervised learning.
You can check the specific algo you're interested in (LSI, LDA, word2vec, etc) to see if it's suitable for your type of data / language. Gensim itself is not concerned with NLP text preprocessing at all, your "tokens" and documents are opaque strings to Gensim.
Problem description
Many NLP libraries exist today that support many NLP related tasks. Unfortunately not all of them support more beyond English and few other languages. My GUESS here is Gensim does support more languages. But Does it?
It would be nice if anywhere in the docs it would be specified that Gensim supports languages X.Y.Z (supports Unicode, has language models, ...) - or even better - language agnostic.
Reproduce
A usual search would be "gensim supported languages".
Versions
<= 3.8.3
The text was updated successfully, but these errors were encountered: