Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment

Siqi Bao, Huang He, Fan Wang, Rongzhong Lian, Hua Wu


Abstract
In this paper, a novel Generation-Evaluation framework is developed for multi-turn conversations with the objective of letting both participants know more about each other. For the sake of rational knowledge utilization and coherent conversation flow, a dialogue strategy which controls knowledge selection is instantiated and continuously adapted via reinforcement learning. Under the deployed strategy, knowledge grounded conversations are conducted with two dialogue agents. The generated dialogues are comprehensively evaluated on aspects like informativeness and coherence, which are aligned with our objective and human instinct. These assessments are integrated as a compound reward to guide the evolution of dialogue strategy via policy gradient. Comprehensive experiments have been carried out on the publicly available dataset, demonstrating that the proposed method outperforms the other state-of-the-art approaches significantly.
Anthology ID:
P19-1535
Volume:
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2019
Address:
Florence, Italy
Editors:
Anna Korhonen, David Traum, Lluís Màrquez
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5382–5391
Language:
URL:
https://aclanthology.org/P19-1535
DOI:
10.18653/v1/P19-1535
Bibkey:
Cite (ACL):
Siqi Bao, Huang He, Fan Wang, Rongzhong Lian, and Hua Wu. 2019. Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5382–5391, Florence, Italy. Association for Computational Linguistics.
Cite (Informal):
Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment (Bao et al., ACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/P19-1535.pdf
Code
 PaddlePaddle/models