maxoodf / word2vec

word2vec++ is a Distributed Representations of Words (word2vec) library and tools implementation, written in C++11 from the scratch
Apache License 2.0
131 stars 24 forks source link

Paragraph Vector algorithms #12

Closed jwijffels closed 3 years ago

jwijffels commented 3 years ago

Do you have any plans to add the distributed bag of words ('PV-DBOW') and the distributed memory ('PV-DM') model?

maxoodf commented 3 years ago

I think modern algorithms based on transformers, such as BERT and GPT, outperform Paragraph Vector, Average Vector and other old school algorithms on most of NLP tasks. So I do not plan to add PV implementations.

jwijffels commented 3 years ago

Ok. Fair enough. Thanks for the response.