search

facebookresearch / fastText

Library for fast text representation and classification.
https://fasttext.cc/
MIT License
25.93k stars 4.72k forks source link

Training character level embeddings #724

Open JoaoLages opened 5 years ago

JoaoLages commented 5 years ago

Is it possible to load/train FastText and incorporate it in a pytorch model so that it can update character level weights and therefore train embeddings for unknown tokens also?

I had a look at this but it seems that all the script does is to load the binary weights file into a word embedding matrix.

zabatani commented 4 years ago

Exactly what I wanted to post, would definitely appreciate such a feature!