Discourse Coherence and Response-Guided Context Rewriting for Multi-Party Dialogue Generation

TL;DR

This paper introduces DRCR, a novel framework that improves multi-party dialogue generation by rewriting dialogue context using discourse coherence and response quality signals, with a self-evolution learning method.

Contribution

The work presents a new context rewriting approach guided by discourse and response signals, along with a dynamic self-evolution training method for multi-party dialogue generation.

Findings

DRCR outperforms baseline models on four multi-party dialogue datasets.

Dialogue context rewriting improves response coherence and relevance.

Self-evolution training enhances the capabilities of the rewriter and responder.

Abstract

Previous research on multi-party dialogue generation has predominantly leveraged structural information inherent in dialogues to directly inform the generation process. However, the prevalence of colloquial expressions and incomplete utterances in dialogues often impedes comprehension and weakens the fidelity of dialogue structure representations, which is particularly pronounced in multi-party dialogues. In this work, we propose a novel framework DRCR (Discourse coherence and Response-guided Context Rewriting) to improve multi-party dialogue generation through dialogue context rewriting. Specifically, DRCR employs two complementary feedback signals, discourse coherence and response quality, to construct preference data for both context rewriting and response generation. Moreover, we propose a dynamic self-evolution learning method that allows the rewriter and responder to continuously enhance their capabilities through mutual interaction in an iterative training loop. Comprehensive experiments conducted on four multi-party dialogue datasets substantiate the effectiveness of DRCR.