GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue Systems
This work addresses the problem of enhancing dialogue system performance for task-oriented applications, representing an incremental advancement through novel graph-based methods.
The paper tackled the challenges of incorporating external knowledge bases and capturing dialogue history semantics in end-to-end task-oriented dialogue systems by integrating graph structural information from knowledge bases and dependency parsing trees, resulting in consistent improvements over state-of-the-art models on two datasets.
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 to effectively incorporate external knowledge bases (KBs) into the learning framework; the other is how to accurately capture the semantics of dialogue history. In this paper, we address these two challenges by exploiting the graph structural information in the knowledge base and in the dependency parsing tree of the dialogue. To effectively leverage the structural information in dialogue history, we propose a new recurrent cell architecture which allows representation learning on graphs. To exploit the relations between entities in KBs, the model combines multi-hop reasoning ability based on the graph structure. Experimental results show that the proposed model achieves consistent improvement over state-of-the-art models on two different task-oriented dialogue datasets.