Re:Understanding word vectors
by hiker512 on Friday March 02, 2018 @12:23PM
(#16503595)
Can you recommend an implementation or paper for handling OOV words via character level embeddings?
[ Parent
| on HN ]
Re:Understanding word vectors
by patelajay285 on Friday March 02, 2018 @12:28PM
(#16503644)
We just open sourced a easy to use library called Magnitude that handles out-of-vocabulary words and uses Annoy indexing for fast most_similar queries for word2vec, GloVE, and fastText:
Thank you very much. This might help with my Master Thesis :)
Great work!
I agree - and also to your initial comments on the actual benefits & limitations of word vectors, that I can 100% subscribe to.
Just an FYI, FastText's default implementation handles OOV words via word n-grams and character n-grams. (see switches -minn, -maxn, and -wordNgram)