Abstract
Task-oriented dialogue generation is challenging since the underlying knowledge is often dynamic and effectively incorporating knowledge into the learning process is hard. It is particularly challenging to generate both human-like and informative responses in this setting. Recent research primarily focused on various knowledge distillation methods where the underlying relationship between the facts in a knowledge base is not effectively captured. In this paper, we go one step further and demonstrate how the structural information of a knowledge graph can improve the system’s inference capabilities. Specifically, we propose DialoKG, a novel task-oriented dialogue system that effectively incorporates knowledge into a language model. Our proposed system views relational knowledge as a knowledge graph and introduces (1) a structure-aware knowledge embedding technique, and (2) a knowledge graph-weighted attention masking strategy to facilitate the system selecting relevant information during the dialogue generation. An empirical evaluation demonstrates the effectiveness of DialoKG over state-of-the-art methods on several standard benchmark datasets.- Anthology ID:
- 2022.findings-naacl.195
- Volume:
- Findings of the Association for Computational Linguistics: NAACL 2022
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Editors:
- Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2557–2571
- Language:
- URL:
- https://aclanthology.org/2022.findings-naacl.195
- DOI:
- 10.18653/v1/2022.findings-naacl.195
- Cite (ACL):
- Md Rashad Al Hasan Rony, Ricardo Usbeck, and Jens Lehmann. 2022. DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 2557–2571, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation (Rony et al., Findings 2022)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2022.findings-naacl.195.pdf
- Code
- rashad101/dialokg
- Data
- MultiWOZ