Dynamic Multi-Scale Context Aggregation for Conversational Aspect-Based Sentiment Quadruple Analysis
This addresses conversational aspect-based sentiment analysis, a domain-specific task, with incremental improvements in capturing long-range context and inter-utterance dependencies.
The paper tackled the problem of extracting target-aspect-opinion-sentiment quadruples in dialogues, where elements span multiple utterances, by proposing a Dynamic Multi-scale Context Aggregation network (DMCA) that uses multi-scale utterance windows and dynamic hierarchical aggregation, achieving state-of-the-art performance with significant improvements over baselines.
Conversational aspect-based sentiment quadruple analysis (DiaASQ) aims to extract the quadruple of target-aspect-opinion-sentiment within a dialogue. In DiaASQ, a quadruple's elements often cross multiple utterances. This situation complicates the extraction process, emphasizing the need for an adequate understanding of conversational context and interactions. However, existing work independently encodes each utterance, thereby struggling to capture long-range conversational context and overlooking the deep inter-utterance dependencies. In this work, we propose a novel Dynamic Multi-scale Context Aggregation network (DMCA) to address the challenges. Specifically, we first utilize dialogue structure to generate multi-scale utterance windows for capturing rich contextual information. After that, we design a Dynamic Hierarchical Aggregation module (DHA) to integrate progressive cues between them. In addition, we form a multi-stage loss strategy to improve model performance and generalization ability. Extensive experimental results show that the DMCA model outperforms baselines significantly and achieves state-of-the-art performance.