GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems

• DOI: 10.18653/v1/2020.emnlp-main.147
• Publication Date: 2020-11-29T09:51:46Z
• Authors: Shiquan Yang; Rui Zhang; Sarah Erfani
• Keywords: Leverage (statistics); Knowledge graph; End-to-end principle

End-to-end task-oriented dialogue systems aim to generate system responses directly from plain text inputs. There are two challenges for such systems: one is how effectively incorporate external knowledge bases (KBs) into the learning framework; other accurately capture semantics of history. In this paper, we address these by exploiting graph structural information in base and dependency parsing tree dialogue. To leverage history, propose a new recurrent cell architecture which allows representation on graphs. exploit relations between entities KBs, model combines multi-hop reasoning ability based structure. Experimental results show that proposed achieves consistent improvement over state-of-the-art models different datasets.