Skip to content

Code for ACL 2023 (Findings) accepted paper titled "TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition"

Notifications You must be signed in to change notification settings

circle-hit/TransESC

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

TransESC

The official implementation for the Findings of ACL 2023 paper TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition.

venue status

Requirements

  • Python 3.7
  • PyTorch 1.8.2
  • Transformers 4.12.3
  • CUDA 11.1

Preparation

Download the processed dataset, annotated emotion and keywords, and generated commonsense knowledge from https://drive.google.com/drive/folders/1rNpa5vDuB7KssQuVBAhkKtmAuqPa0Qgf?usp=sharing. Then place them in /dataset.

Training

python main.py

Evaluation and Generation

python main.py --test 

Citation

If you find our work useful for your research, please kindly cite our paper as follows:

@article{zhao2023transesc,
  title={TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition},
  author={Zhao, Weixiang and Zhao, Yanyan and Wang, Shilong and Qin, Bing},
  journal={arXiv preprint arXiv:2305.03296},
  year={2023}
}

About

Code for ACL 2023 (Findings) accepted paper titled "TransESC: Smoothing Emotional Support Conversation via Turn-Level State Transition"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages