@inproceedings{smith-etal-2022-human, title = "Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents", author = "Smith, Eric and Hsu, Orion and Qian, Rebecca and Roller, Stephen and Boureau, Y-Lan and Weston, Jason", editor = "Liu, Bing and Papangelis, Alexandros and Ultes, Stefan and Rastogi, Abhinav and Chen, Yun-Nung and Spithourakis, Georgios and Nouri, Elnaz and Shi, Weiyan", booktitle = "Proceedings of the 4th Workshop on NLP for Conversational AI", month = may, year = "2022", address = "Dublin, Ireland", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2022.nlp4convai-1.8/", doi = "10.18653/v1/2022.nlp4convai-1.8", pages = "77--97" }