DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation

TL;DR

DialoKG is a novel dialogue system that leverages knowledge graph structures through specialized embedding and attention strategies to generate more informative and human-like responses in task-oriented dialogues.

Contribution

It introduces a structure-aware knowledge embedding and a graph-weighted attention mechanism to better incorporate knowledge graphs into dialogue generation.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Effectively captures relational knowledge for improved responses.

Enhances inference capabilities in knowledge-based dialogue systems.

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.