search

declare-lab / MIME

This repository contains PyTorch implementations of the models from the paper An Empirical Study MIME: MIMicking Emotions for Empathetic Response Generation.
MIT License
43 stars 11 forks source link

Question about the output.txt #2

Closed LeiShenVictoria closed 3 years ago

LeiShenVictoria commented 3 years ago

Hi, I found that the responses provided in output.txt are not similar to what you mentioned in your paper.

E.g., emotion:apprehensive vader-score: -0.6606 predicted_emotion: afraid Context:['i went skydiving last summer with my partner . it was so scary !', 'wow , that is scary . were you nervous ?', 'absolutely ! i have always been scared of heights , but i am so glad i made myself .'] Topk:that sounds like fun ! Beam: i am sorry to hear that . i hope you have a good time ! Greedy:i am sorry to hear that . i hope you get it ! Ref:it sounds like a great experience !

While the response for this case in your paper is "That must've been a very beautiful memory."

nmder commented 3 years ago

Hi,

This is normal as there is randomness in the model stemmed from sampling. Hope this resolves your doubt.

Thanks!

LeiShenVictoria commented 3 years ago

Could you pls provide the output.txt you used in your paper? Thanks