TY - GEN
T1 - Learning to Express in Knowledge-Grounded Conversation
AU - Zhao, Xueliang
AU - Fu, Tingchen
AU - Tao, Chongyang
AU - Wu, Wei
AU - Zhao, Dongyan
AU - Yan, Rui
N1 - Publisher Copyright:
© 2022 Association for Computational Linguistics.
PY - 2022
Y1 - 2022
N2 - Grounding dialogue generation by extra knowledge has shown great potentials towards building a system capable of replying with knowledgeable and engaging responses. Existing studies focus on how to synthesize a response with proper knowledge, yet neglect that the same knowledge could be expressed differently by speakers even under the same context. In this work, we mainly consider two aspects of knowledge expression, namely the structure of the response and style of the content in each part. We therefore introduce two sequential latent variables to represent the structure and the content style respectively. We propose a segmentation-based generation model and optimize the model by a variational approach to discover the underlying pattern of knowledge expression in a response. Evaluation results on two benchmarks indicate that our model can learn the structure style defined by a few examples and generate responses in desired content style.
AB - Grounding dialogue generation by extra knowledge has shown great potentials towards building a system capable of replying with knowledgeable and engaging responses. Existing studies focus on how to synthesize a response with proper knowledge, yet neglect that the same knowledge could be expressed differently by speakers even under the same context. In this work, we mainly consider two aspects of knowledge expression, namely the structure of the response and style of the content in each part. We therefore introduce two sequential latent variables to represent the structure and the content style respectively. We propose a segmentation-based generation model and optimize the model by a variational approach to discover the underlying pattern of knowledge expression in a response. Evaluation results on two benchmarks indicate that our model can learn the structure style defined by a few examples and generate responses in desired content style.
UR - https://www.scopus.com/pages/publications/85138376925
U2 - 10.18653/v1/2022.naacl-main.164
DO - 10.18653/v1/2022.naacl-main.164
M3 - 会议稿件
AN - SCOPUS:85138376925
T3 - NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference
SP - 2258
EP - 2273
BT - NAACL 2022 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
T2 - 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2022
Y2 - 10 July 2022 through 15 July 2022
ER -