Are there any reference document(s) that give a comprehensive list combination techniques for word-level embeddings along with their pros/cons (and ideally some pointers to publications where they were successful or not so successful)?

Example of combination techniques for word-level embeddings: sum.

enter image description here


The team around Bengio published an article a few years ago. Maybe this is good enough?

Turian, J., Ratinov, L., & Bengio, Y. (2010). Word representations: a simple and general method for semi-supervised learning (pp. 384–394). Association for Computational Linguistics.


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.