通过语义解耦和图对齐进行对话中的情感-原因对提取
Emotion-Cause Pair Extraction in Conversations via Semantic Decoupling and Graph Alignment
AI总结：
本文提出SCALE框架，通过语义解耦和图对齐方法，解决对话中情感与原因关系的提取问题，实现多对多的全局一致匹配。
摘要：
情感-原因对提取（ECPEC）旨在识别对话中情感陈述与其触发原因之间的因果关系。现有方法将ECPEC视为独立的成对分类任务，忽视了情感扩散和原因解释的语义差异，未能捕捉到全局一致的多对多对话因果性。为解决这些问题，我们从语义角度重新审视ECPEC，旨在解耦情感导向的语义与原因导向的语义，将它们映射到两个互补的表示空间中，以更好地捕捉它们的对话角色。基于这种语义解耦，我们自然地将ECPEC表述为情感侧和原因侧表示之间的全局对齐问题，并利用最优传输来实现多对多和全局一致的情感-原因匹配。基于此视角，我们提出了一个统一的框架SCALE，在共享的对话结构中实例化上述语义解耦和对齐原则。在多个基准数据集上的广泛实验表明，SCALE在多个基准数据集上实现了最先进的性能。我们的代码已发布在https://github.com/CoCoSphere/SCALE。
英文摘要：
Emotion-Cause Pair Extraction in Conversations (ECPEC) aims to identify the set of causal relations between emotion utterances and their triggering causes within a dialogue. Most existing approaches formulate ECPEC as an independent pairwise classification task, overlooking the distinct semantics of emotion diffusion and cause explanation, and failing to capture globally consistent many-to-many conversational causality. To address these limitations, we revisit ECPEC from a semantic perspective and seek to disentangle emotion-oriented semantics from cause-oriented semantics, mapping them into two complementary representation spaces to better capture their distinct conversational roles. Building on this semantic decoupling, we naturally formulate ECPEC as a global alignment problem between the emotion-side and cause-side representations, and employ optimal transport to enable many-to-many and globally consistent emotion-cause matching. Based on this perspective, we propose a unified framework SCALE that instantiates the above semantic decoupling and alignment principle within a shared conversational structure. Extensive experiments on several benchmark datasets demonstrate that SCALE consistently achieves state-of-the-art performance. Our codes are released at https://github.com/CoCoSphere/SCALE.
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。
