News for hackers. Stuff that matters.
Re:Facebook releases 300-dimensional pretrained Fasttext vec... by exgrv on Thursday March 02, 2017 @09:59AM (#13774407)
Models are trained independently for each language. So unfortunately, you cannot directly compare words from different languages using these vectors.

If you have a bilingual dictionary, you might try to learn a linear mapping from one language to the other (e.g. see https://arxiv.org/abs/1309.4168 for this approach).

There are no comments on this comment yet.