README.md

USDA

Dataset

Due to the absence of data split in the original USS dataset, we split each dataset by 8:1:1 for train-valid-test set and filter out the dialogues with less than 2 turns.

Please cite the following paper if you use this dataset in any way：

• Weiwei Sun, Shuo Zhang, Krisztian Balog, Zhaochun Ren, Pengjie Ren, Zhumin Chen, Maarten de Rijke. Simulating User Satisfaction for the Evaluation of Task-oriented Dialogue Systems. In SIGIR 2021.

Citation

If the data or code is used in your research, please star this repo and cite our paper as follows:

@inproceedings{www2022-usda,
  author    = {Yang Deng and
               Wenxuan Zhang and
               Wai Lam and
               Hong Cheng and
               Helen Meng},
  title     = {User Satisfaction Estimation with Sequential Dialogue Act Modeling
               in Goal-oriented Conversational Systems},
  booktitle = {{WWW} '22: The Web Conference 2022},
  year      = {2022},
}