fastText versus word2vec
According to the following preliminary comparison by Gensim:
fastText embeddings are significantly better than word2vec at encoding syntactic information. This is expected, since most syntactic analogies are morphology based, and the char n-gram approach of fastText takes such information into account. The original word2vec model seems to perform better on semantic tasks, since words in semantic analogies are unrelated to their char n-grams, and the added information from irrelevant char n-grams worsens the embeddings.
The source for this is: word2vec fasttext comparison notebook (https://github.com/RaRe-Technologies/gensim/blob/37e49971efa74310b300468a5b3cf531319c6536/docs/notebooks/Word2Vec_FastText_Comparison.ipynb ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access