Multimodal Word Distributions — mentioned by aisofteng

Sat, 03 Mar 2018 18:07:51 GMT

>Another problem of word vectors is that any word might actually have multiple senses, while vectors are just point estimates. If we wanted to be correct, we needed first to find the right sense for each word in a phrase and only then assign the vector. There is research in "on-the-fly" word vectors that adapt to context, but it's much harder to use. There has been work on representing words not as vectors but as multimodal Gaussian distributions in order to try to deal with polysemy, such as [0], of which an implementation (which I have not tried to use) is available on GitHub at [1]. >It…

Paper and discussion history. A mention is not an endorsement.

Multimodal Word Distributions · HackerPapers discussions

Multimodal Word Distributions — mentioned by aisofteng