RT-KGD: Relation Transition Aware Knowledge-Grounded Dialogue Generation

TL;DR

This paper introduces RT-KGD, a dialogue generation model that leverages relation transition regularities in knowledge graphs and multi-turn context to produce more coherent and relevant responses.

Contribution

It proposes a novel relation transition aware framework that integrates dialogue-level relation patterns with turn-level entity semantics for knowledge-grounded dialogue generation.

Findings

Outperforms state-of-the-art baselines in automatic evaluations.

Achieves higher coherence and relevance in generated responses.

Effectively utilizes relation transition regularities in knowledge graphs.

Abstract

Grounding dialogue system with external knowledge is a promising way to improve the quality of responses. Most existing works adopt knowledge graphs (KGs) as the external resources, paying attention to the contribution of entities in the last utterance of the dialogue for context understanding and response generation. Nevertheless, the correlations between knowledge implied in the multi-turn context and the transition regularities between relations in KGs are under-explored. To this end, we propose a Relation Transition aware Knowledge-Grounded Dialogue Generation model (RT-KGD). Specifically, inspired by the latent logic of human conversation, our model integrates dialogue-level relation transition regularities with turn-level entity semantic information. In this manner, the interaction between knowledge is considered to produce abundant clues for predicting the appropriate knowledge and generating coherent responses. The experimental results on both automatic evaluation and manual evaluation indicate that our model outperforms state-of-the-art baselines.