Closed jmugan closed 8 years ago
Did you do it with ubuntu dataset ?
You use beam decoder only for evaluation
Different dataset. Thanks for the response. I'll try it on just the evaluation.
@jmugan Could you please share your results?
Sure. I try it in the next few days and let you know how it comes out.
How do you tell which of the beams returned the best sequence? In line 253 of neural_conversation_model.py
the output to step
is
path, symbol , output_logits = model.step(sess, encoder_inputs, decoder_inputs,
target_weights, bucket_id, True,beam_search )
Here, output_logits
is not used, as far as I can tell. It is a list of length output_size
where each entry is a length of beam_size
but how is it different from symbol
?
Using symbol
and path
you put together the beam_size
responses, but which is best? Why doesn't output_logits
have their cost?
You do depending on the task. In Smart Reply they find diverse replies depending on how different replies are using semi supervised clustering . Right now. they are sorted on lowest perplexity but that might not be best replies you are looking for
Cool code. In beam_attention_decoder, I get an error at line 615
It looks like maybe
y
takes the beams into account buthidden_features[a]
does not.The stack trace looks like