I have two word embeddings $w_1$ and $w_2$ with dimension 100 as input to a convolutional neural network. It should learn the similarity between these two words.

I am now concerned with the applied convolution operation. What is a reasonable filter size? In which way should the convolution operation perform on the two word embeddings?


Your Answer

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

Browse other questions tagged or ask your own question.