GlobalMaksimum / sadedegel

A General Purpose NLP library for Turkish
http://sadedegel.ai
MIT License
93 stars 13 forks source link

Doc2Vec Implementation #136

Open dafajon opened 4 years ago

dafajon commented 4 years ago

After Bert and TfIdf vectors, Word2Vec will come into play. Just as there is TfIdf for document level. Implement a Doc2Vec model with current extended corpus.

dafajon commented 4 years ago

Current Doc2Vec will be mean of Word2Vec vectors. Gensin will be utilized again for Doc2Vec training.