Advancing Multi-Party Dialogue Framework with Speaker-ware Contrastive Learning

TL;DR

This paper introduces CMR, a novel contrastive learning framework for multi-party dialogue response generation that captures speaker styles and thematic shifts, outperforming existing models and enhancing large language models' capabilities.

Contribution

It is the first to apply contrastive learning to multi-party dialogue generation, addressing limitations of graph-based methods and improving response quality.

Findings

CMR significantly outperforms state-of-the-art models.

It generalizes well to large pre-trained language models.

Enhances handling of multi-party conversations.

Abstract

Multi-party dialogues, common in collaborative scenarios like brainstorming sessions and negotiations, pose significant challenges due to their complexity and diverse speaker roles. Current methods often use graph neural networks to model dialogue context, capturing structural dynamics but heavily relying on annotated graph structures and overlooking individual speaking styles. To address these challenges, we propose CMR, a Contrastive learning-based Multi-party dialogue Response generation framework. CMR employs a two-stage self-supervised contrastive learning framework. First, it captures global differences in speaking styles across individuals. Then, it focuses on intra-conversation comparisons to identify thematic transitions and contextually relevant facts. To the best of our knowledge, this is the first approach that applies contrastive learning in multi-party dialogue generation. Experimental results demonstrate that CMR not only significantly outperforms state-of-the-art models, but also generalizes well to large pre-trained language models, effectively enhancing their capability in handling multi-party conversations.