Advancing Multi-Party Dialogue Framework with Speaker-ware Contrastive Learning
This addresses the problem of complex multi-party dialogue generation for applications like brainstorming and negotiations, representing an incremental advancement by applying contrastive learning to this domain.
The paper tackled the challenge of generating responses in multi-party dialogues by proposing CMR, a contrastive learning-based framework that captures speaking styles and thematic transitions, resulting in significant performance improvements over state-of-the-art models and enhanced generalization to large pre-trained language models.
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.