Open SionHu opened 3 years ago
Well, the issue is that you need to give a POS tag to each word before it can disambiguate which vector to choose when doing the final pooling of your word vectors into a sentence vector.
Maybe you can use a POS tagger for this?
Thanks so much for the great work and nice documentation!
I have a question regarding using the sense2vec to find the similarity score between 2 sentences. For example, "What is the color of the airplane?" and "what are the colors of these planes" should have a very high similarity score.
I found the related section in your document discussing how to achieve this for words, but didn't find any for sentences.
Could you tell me where can I find the related information? Thanks ahead!