Span-level emotion-cause-category triplet extraction with instruction tuning LLMs and data augmentation

Abstract

Span-level emotion-cause-category triplet extraction is a fine-grained task in emotion cause analysis that aims to identify emotion spans, cause spans, and their corresponding emotion categories from documents. Existing methods, including clause-level emotion-cause pair extraction and span-level emotion-cause detection, often suffer from redundant information and difficulties in accurately classifying emotion categories, particularly when emotions are expressed implicitly or ambiguously. To overcome these challenges, this study explores a fine-grained approach to span-level emotion-cause-category triplet extraction and introduces an innovative framework that leverages instruction tuning and data augmentation techniques based on large language models. The proposed method employs task-specific triplet extraction instructions and utilizes low-rank adaptation to fine-tune large language models, eliminating the necessity for intricate task-specific architectures. Furthermore, an LLM-based data augmentation strategy is developed to address data scarcity by guiding large language models in generating high-quality synthetic training data. Extensive experimental evaluations demonstrate that the proposed approach significantly outperforms existing baseline methods, achieving at least a 12.8 % improvement in span-level emotion-cause-category triplet extraction metrics. The results demonstrate the method’s effectiveness and robustness, offering a promising avenue for advancing research in emotion cause analysis.