Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation
Jun Xu, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che, Ting Liu
Abstract
To address the challenge of policy learning in open-domain multi-turn conversation, we propose to represent prior information about dialog transitions as a graph and learn a graph grounded dialog policy, aimed at fostering a more coherent and controllable dialog. To this end, we first construct a conversational graph (CG) from dialog corpora, in which there are vertices to represent “what to say” and “how to say”, and edges to represent natural transition between a message (the last utterance in a dialog context) and its response. We then present a novel CG grounded policy learning framework that conducts dialog flow planning by graph traversal, which learns to identify a what-vertex and a how-vertex from the CG at each turn to guide response generation. In this way, we effectively leverage the CG to facilitate policy learning as follows: (1) it enables more effective long-term reward design, (2) it provides high-quality candidate actions, and (3) it gives us more control over the policy. Results on two benchmark corpora demonstrate the effectiveness of this framework.- Anthology ID:
- 2020.acl-main.166
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1835–1845
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.166
- DOI:
- 10.18653/v1/2020.acl-main.166
- Cite (ACL):
- Jun Xu, Haifeng Wang, Zheng-Yu Niu, Hua Wu, Wanxiang Che, and Ting Liu. 2020. Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1835–1845, Online. Association for Computational Linguistics.
- Cite (Informal):
- Conversational Graph Grounded Policy Learning for Open-Domain Conversation Generation (Xu et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/naacl-24-ws-corrections/2020.acl-main.166.pdf