ProphetChat: Enhancing Dialogue Generation with Simulation of Future Conversation

Chang Liu, Xu Tan, Chongyang Tao, Zhenxin Fu, Dongyan Zhao, Tie-Yan Liu, Rui Yan


Abstract
Typical generative dialogue models utilize the dialogue history to generate the response. However, since one dialogue utterance can often be appropriately answered by multiple distinct responses, generating a desired response solely based on the historical information is not easy. Intuitively, if the chatbot can foresee in advance what the user would talk about (i.e., the dialogue future) after receiving its response, it could possibly provide a more informative response. Accordingly, we propose a novel dialogue generation framework named ProphetChat that utilizes the simulated dialogue futures in the inference phase to enhance response generation. To enable the chatbot to foresee the dialogue future, we design a beam-search-like roll-out strategy for dialogue future simulation using a typical dialogue generation model and a dialogue selector. With the simulated futures, we then utilize the ensemble of a history-to-response generator and a future-to-response generator to jointly generate a more informative response. Experiments on two popular open-domain dialogue datasets demonstrate that ProphetChat can generate better responses over strong baselines, which validates the advantages of incorporating the simulated dialogue futures.
Anthology ID:
2022.acl-long.68
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
962–973
Language:
URL:
https://aclanthology.org/2022.acl-long.68
DOI:
10.18653/v1/2022.acl-long.68
Bibkey:
Cite (ACL):
Chang Liu, Xu Tan, Chongyang Tao, Zhenxin Fu, Dongyan Zhao, Tie-Yan Liu, and Rui Yan. 2022. ProphetChat: Enhancing Dialogue Generation with Simulation of Future Conversation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 962–973, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
ProphetChat: Enhancing Dialogue Generation with Simulation of Future Conversation (Liu et al., ACL 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2022.acl-long.68.pdf
Data
DailyDialog