I would need to determine the difference in meaning between the following two sentences:

I am at home
I am not at home
I am at the office

the first two sentences differs in verb, which changes the meaning of the sentences (to negative); the second one, with the first one, differs because of the place. I have thought of word2vec, but I am not completely sure if this is the best tool to analyse sentences like the above ones. Also cosine_similarity could be a solution, but I would have not information about the meaning. I think it is more about semantic meaning...


Out of the box, something like Google's Universal Sentence Encoder (USE) may work for your use-case. Many of the common NLP embedding techniques nowadays work on individual words and so creating sentence-level embeddings means averaging multiple word-level vectors together. USE was built to operate at the sentence level, so you may find it better.

The original paper can be found here: https://arxiv.org/abs/1803.11175

An example blog post leveraging USE: https://medium.com/@gaurav5430/universal-sentence-encoding-7d440fd3c7c7


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.