Author(s): Gu, Xue ; Meng, Ziyao ; Gomes, Tiago Manuel Ribeiro ; Tavares, Adriano ; Xu, Hao
Date: 2024
Persistent ID: https://hdl.handle.net/1822/98148
Origin: RepositóriUM - Universidade do Minho
Subject(s): Emotion-cause pair extraction; Large language model; Symbolic reasoning; Sentiment analysis; Experiencer; Multi-step Reasoning Problem
Emotion-cause pair extraction (ECPE) aims to identify all emotion and cause clauses in documents, forming emotion-cause pairs (ECPs). Although existing methods have achieved some success, they face issues such as overlooking the impact of emotion experiencers, failing to leverage specific domain knowledge, and tending to spurious correlations. To address these issues, we transform the ECPE task into a multi-step reasoning problem and propose the Emotion-Experiencer-Event-Cause (EEEC) multi-step framework. EEEC combines symbolic prior reasoning with large language model (LLM) inference to improve precision and interpretability. Specifically, we design a lightweight symbolic filtering module that uses sentiment lexicons and interpretable rules to pre-select candidate emotion clauses, thereby reducing the reasoning space and guiding the LLM toward emotionally salient content. Furthemore, we introduce an experiencer identification task to understand the source of emotions and enhance the association between emotion and cause clauses. In addition, by combining both prior knowledge and induced reasoning, EEEC guides a large-scale language model (LLM) to perform the ECPE task efficiently. Experimental results demonstrate that EEEC achieves performance close to current state-of-the-art supervised fine-tuning methods.
