@inproceedings{raddleanevaluationbenchmarkandanalysis,
  title = {RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems},
  author = {Baolin Peng and Chunyuan Li and Zhu Zhang and Chenguang Zhu and Jinchao Li and Jianfeng Gao},
  year = {2020},
  booktitle = {ACL 2021 5},
  eprint = {2012.14666},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2012.14666v1},
}