I have a seq2seq model (already trained on some dataset). Now, I want to rank candidate responses to input text from most relevant to the least one. I tried to use hidden state of encoder and decoder and multiply them to find the best candidate but I'm not sure if this is the right way. Can anyone suggest a solution or even a code for this problem?


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.