TCDA: Thread-Constrained Discourse-Aware Modeling for Conversational Sentiment Quadruple Analysis

TL;DR

This paper introduces TCDA, a novel framework combining thread-constrained DAG and discourse-aware position embeddings, to improve conversational sentiment analysis by capturing dialogue structure and temporal dynamics.

Contribution

It proposes a new modeling approach that effectively filters noise, maintains global connectivity, and captures thread dependencies in multi-turn dialogues.

Findings

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

Effectively filters cross-thread noise and maintains dialogue structure.

Alleviates Distance Dilution problem in token-level modeling.

Abstract

Conversational Aspect-based Sentiment Quadruple Analysis (DiaASQ) needs to capture the complex interrelationships in multiple rounds of dialogues. Existing methods usually employ simple Graph Convolutional Networks (GCN), which introduce structural noise and fail to consider the temporal sequence of the dialogues, or use standard RoPE, which implicitly captures relative distances in a flat sequence but cannot clearly separate the token-level syntactic order from the utterance-level progression, and may suffer from the Distance Dilution problem. To address these issues, we propose a new framework that combines Thread-Constrained Directed Acyclic Graph (TC-DAG) and Discourse-Aware Rotary Position Embedding (D-RoPE). Specifically, TC-DAG filters out cross-thread noise based on thread constraints, maintains global connectivity through root anchoring, and incorporates the temporal sequence of the dialogues. D-RoPE aligns multi-layer semantics using dual-stream projection and multi-scale frequency signals, captures thread dependencies using tree-like distances, and alleviates the token-level Distance Dilution problem by incorporating utterance-level progressions. Experimental results on two benchmark datasets demonstrate that our framework achieves state-of-the-art performance.