Open mossaab0 opened 8 years ago
I put that model in the seq2seq
folder. It was kind of an experimental model where I generated answers for each question using an RNN model like Karpathy's char-rnn, then used the generated answers instead of the questions for the Embedding model (this might be cheating). But once you generate the answers for all the questions you can change this line.
Hi,
I can't find the implementation of this model that was added recently to the results, and that appears to perform much better than the other ones.