Abstract
We study a symmetric collaborative dialogue setting in which two agents, each with private knowledge, must strategically communicate to achieve a common goal. The open-ended dialogue state in this setting poses new challenges for existing dialogue systems. We collected a dataset of 11K human-human dialogues, which exhibits interesting lexical, semantic, and strategic elements. To model both structured knowledge and unstructured language, we propose a neural model with dynamic knowledge graph embeddings that evolve as the dialogue progresses. Automatic and human evaluations show that our model is both more effective at achieving the goal and more human-like than baseline neural and rule-based models.- Anthology ID:
- P17-1162
- Volume:
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2017
- Address:
- Vancouver, Canada
- Editors:
- Regina Barzilay, Min-Yen Kan
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1766–1776
- Language:
- URL:
- https://aclanthology.org/P17-1162
- DOI:
- 10.18653/v1/P17-1162
- Cite (ACL):
- He He, Anusha Balakrishnan, Mihail Eric, and Percy Liang. 2017. Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1766–1776, Vancouver, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Learning Symmetric Collaborative Dialogue Agents with Dynamic Knowledge Graph Embeddings (He et al., ACL 2017)
- PDF:
- https://preview.aclanthology.org/naacl24-info/P17-1162.pdf
- Code
- worksheets/0xc757f29f + additional community code
- Data
- MutualFriends