Is there a seq-to-seq model which does not require to know the start and end of a sentence? I need to model a system which gets a long sequence of words and creates a long sequence of tokens as long as the input. For example it takes a sequence of 1000 words and creates a sequence of 1000 tokens, each token corresponds to an input word.

  • $\begingroup$ What do you mean? You mean a system that tokenize a sentence? A system taht does that do that does not need teh start of the sequence and anchor not does it uses a neural network based approach. $\endgroup$ Dec 8 '19 at 6:09
  • $\begingroup$ So, isn't there any model that creates a seq-to-seq model without tokenizing? $\endgroup$
    – Atena
    Dec 24 '19 at 8:46

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.