TY - GEN
T1 - There Is No Standard Answer
T2 - 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
AU - Zhao, Xueliang
AU - Fu, Tingchen
AU - Tao, Chongyang
AU - Yan, Rui
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - Knowledge-grounded conversation (KGC) shows excellent potential to deliver an engaging and informative response. However, existing approaches emphasize selecting one golden knowledge given a particular dialogue context, overlooking the one-to-many phenomenon in dialogue. As a result, the existing paradigm limits the diversity of knowledge selection and generation. To this end, we establish a multi-reference KGC dataset and propose a series of metrics to systematically assess the one-to-many efficacy of existing KGC models. Furthermore, to extend the hypothesis space of knowledge selection to enhance the mapping relationship between multiple knowledge and multiple responses, we devise a span-based variational model and optimize the model in a wake-sleep style with an ameliorated evidence lower bound objective to learn the one-to-many generalization. Both automatic and human evaluations demonstrate the efficacy of our approach.
AB - Knowledge-grounded conversation (KGC) shows excellent potential to deliver an engaging and informative response. However, existing approaches emphasize selecting one golden knowledge given a particular dialogue context, overlooking the one-to-many phenomenon in dialogue. As a result, the existing paradigm limits the diversity of knowledge selection and generation. To this end, we establish a multi-reference KGC dataset and propose a series of metrics to systematically assess the one-to-many efficacy of existing KGC models. Furthermore, to extend the hypothesis space of knowledge selection to enhance the mapping relationship between multiple knowledge and multiple responses, we devise a span-based variational model and optimize the model in a wake-sleep style with an ameliorated evidence lower bound objective to learn the one-to-many generalization. Both automatic and human evaluations demonstrate the efficacy of our approach.
UR - https://www.scopus.com/pages/publications/85149441917
U2 - 10.18653/v1/2022.emnlp-main.123
DO - 10.18653/v1/2022.emnlp-main.123
M3 - 会议稿件
AN - SCOPUS:85149441917
T3 - Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
SP - 1878
EP - 1891
BT - Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022
A2 - Goldberg, Yoav
A2 - Kozareva, Zornitsa
A2 - Zhang, Yue
PB - Association for Computational Linguistics (ACL)
Y2 - 7 December 2022 through 11 December 2022
ER -