From Persona to Person: Enhancing the Naturalness with Multiple Discourse Relations Graph Learning in Personalized Dialogue Generation

TL;DR

This paper introduces MUDI, a graph learning approach that leverages discourse relations and persona information to generate more natural and coherent personalized dialogue responses, improving human-like interaction quality.

Contribution

The paper presents a novel graph-based framework with discourse relation annotation and coherence-aware attention for enhanced personalized dialogue generation.

Findings

Significant improvement in response quality and coherence.

Effective use of discourse relations for personalization.

Enhanced human-likeness in dialogue responses.

Abstract

In dialogue generation, the naturalness of responses is crucial for effective human-machine interaction. Personalized response generation poses even greater challenges, as the responses must remain coherent and consistent with the user's personal traits or persona descriptions. We propose MUDI ($\textbf{Mu}$ltiple $\textbf{Di}$scourse Relations Graph Learning) for personalized dialogue generation. We utilize a Large Language Model to assist in annotating discourse relations and to transform dialogue data into structured dialogue graphs. Our graph encoder, the proposed DialogueGAT model, then captures implicit discourse relations within this structure, along with persona descriptions. During the personalized response generation phase, novel coherence-aware attention strategies are implemented to enhance the decoder's consideration of discourse relations. Our experiments demonstrate significant improvements in the quality of personalized responses, thus resembling human-like dialogue exchanges.