利用说话人感知对比学习改进多方对话框架
Advancing Multi-Party Dialogue Framework with Speaker-ware Contrastive Learning
AI总结：
针对现有多方对话方法依赖图结构标注、忽略个体说话风格的问题，提出基于两阶段自监督对比学习的CMR框架，是首个将对比学习用于多方对话生成的方法，性能优于SOTA且可提升大模型的多方对话处理能力。
摘要：
多方对话常见于头脑风暴会议、谈判等协作场景，因其复杂性和多样的说话人角色带来了巨大挑战。现有方法通常使用图神经网络建模对话上下文，虽能捕捉结构动态，但严重依赖标注好的图结构，且忽略了个体说话风格。为解决这些问题，我们提出CMR——一种基于对比学习的多方对话回复生成框架。CMR采用两阶段自监督对比学习框架：首先捕捉不同个体说话风格的全局差异，随后聚焦于对话内部的对比以识别主题转换和上下文相关事实。据我们所知，这是首个将对比学习应用于多方对话生成的方法。实验结果表明，CMR不仅显著优于现有最优模型，还能很好地泛化到大型预训练语言模型上，有效提升其处理多方对话的能力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
