search

lwgkzl / MultiESC

This is the repository of EMNLP'2022 paper: "Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning".
36 stars 1 forks source link

Are the strategy sequence generator and the utterance decoder trained jointly? #5

Closed lcxxxasd closed 1 year ago

lcxxxasd commented 1 year ago

Hello, the training procedure part of the paper says that ssg and utt decoder are trained joint, but they seem to be trained independently according to the code

YiCheng98 commented 1 year ago

Thank you for pointing out the mistake in our paper.

We experimented with both the joint training and the pipeline fashion. It turned out that the pipeline way was more efficient and competitive, so we finally chose it for all the experiments. The illustration about this part in the appendix of the paper is mistaken. We will revise it and upload a new version at arxiv.