CODEWITHSUNDEEP
machine-learningnlpword2vecgensim
Navin Kumar
Navin Kumar

Reputation: 160

Word embedding for OOV words

I have generated word vectors from a corpus, but I am facing out of vocabulary issues for many words. How can I generate word vectors for OOV words on the fly using existing word embedding?

Upvotes: 4

Views: 5330

Answers (1)

ozgur
ozgur

Reputation: 2719

A very late answer (not even the answer you are looking for) but, with skip-gram models what you ask is almost impossible because each word is a distinct entity in and of itself.

The feature you ask can be done with FastText out of the box. It generates OOV word vectors using it's n-grams.

Gensim has a high-level API to use FastText.

Upvotes: 2

Related Questions