Dynamic Multi-Scale Context Aggregation for Conversational Aspect-Based Sentiment Quadruple Analysis

TL;DR

This paper introduces DMCA, a novel network that captures multi-scale conversational context for better extraction of sentiment quadruples in dialogues, outperforming existing methods.

Contribution

The paper proposes a dynamic multi-scale context aggregation network with hierarchical aggregation and multi-stage loss for improved conversational sentiment analysis.

Findings

DMCA outperforms baseline models significantly.

Achieves state-of-the-art performance on benchmark datasets.

Effectively captures long-range inter-utterance dependencies.

Abstract

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.