Human Evaluation of Conversations is an Open Problem: comparing the sensitivity of various methods for evaluating dialogue agents Eric Smith author Orion Hsu author Rebecca Qian author Stephen Roller author Y-Lan Boureau author Jason Weston author 2022-05 text Proceedings of the 4th Workshop on NLP for Conversational AI Bing Liu editor Alexandros Papangelis editor Stefan Ultes editor Abhinav Rastogi editor Yun-Nung Chen editor Georgios Spithourakis editor Elnaz Nouri editor Weiyan Shi editor Association for Computational Linguistics Dublin, Ireland conference publication smith-etal-2022-human 10.18653/v1/2022.nlp4convai-1.8 https://aclanthology.org/2022.nlp4convai-1.8/ 2022-05 77 97