RT-KGD: Relation Transition Aware Knowledge-Grounded Dialogue Generation
This work addresses the challenge of generating more coherent and knowledge-rich responses in dialogue systems, representing an incremental improvement over existing methods.
The paper tackled the problem of improving knowledge-grounded dialogue generation by addressing under-explored correlations in multi-turn context and relation transitions in knowledge graphs, resulting in a model that outperformed state-of-the-art baselines in evaluations.
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.