TCDA：面向对话情感四元分析的线程约束话语感知建模

摘要

对话式方面级情感四元分析(DiaASQ)需要捕捉多轮对话中的复杂关联关系。现有方法通常采用简单图卷积网络(GCN)，但会引入结构噪声且未考虑对话时序；或使用标准RoPE技术，虽能隐式捕捉扁平序列中的相对距离，但无法清晰分离词级句法顺序与话语级推进关系，且存在距离稀释问题。为此，我们提出融合线程约束有向无环图(TC-DAG)与语篇感知旋转位置编码(D-RoPE)的新框架。具体而言，TC-DAG基于线程约束过滤跨线程噪声，通过根节点锚定保持全局连通性，并融入对话时序信息；D-RoPE采用双流投影与多尺度频率信号对齐多层语义，利用树状距离捕捉线程依赖，并通过引入话语级推进缓解词级距离稀释问题。在两个基准数据集上的实验结果表明，本框架实现了最先进的性能表现。

English

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.

TCDA：面向对话情感四元分析的线程约束话语感知建模

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

摘要

Support