用动态超图建模细粒度情感关系，提升短文本情感分析效果
From Graphs to Hypergraphs: Enhancing Aspect-Based Sentiment Analysis via Multi-Level Relational Modeling
- 基于样本自适应聚类构建动态超边，捕捉多层级语义关联
- 在三个基准上优于主流图模型，尤其搭配RoBERTa时提升显著
- 适合处理短文本、低资源场景下的情感分析任务
方面级情感分析（ABSA）需为特定方面词预测情感极性，但因不同方面间存在情感冲突，且短文本上下文稀疏，难度较大。已有图方法仅建模成对依赖关系，需构建多个关系图，导致冗余、参数开销大及融合时误差传播，限制了在短文本、低资源场景下的鲁棒性。我们提出HyperABSA，一种动态超图框架，通过样本特定的分层聚类诱导方面-观点结构。为构建超边，引入新颖的加速-回退截断机制，自适应决定聚类粒度。在三个基准（Lap14、Rest14、MAMS）上的实验表明，相比强基线图模型有持续提升，与RoBERTa结合时增益显著。结果表明动态超图构造是ABSA中高效而强大的替代方案，且可扩展至其他短文本NLP任务。
原文摘要 · Abstract (English)
Aspect-Based Sentiment Analysis (ABSA) predicts sentiment polarity for specific aspect terms, a task made difficult by conflicting sentiments across aspects and the sparse context of short texts. Prior graph-based approaches model only pairwise dependencies, forcing them to construct multiple graphs for different relational views. These introduce redundancy, parameter overhead, and error propagation during fusion, limiting robustness in short-text, low-resource settings. We present HyperABSA, a dynamic hypergraph framework that induces aspect-opinion structures through sample-specific hierarchical clustering. To construct these hyperedges, we introduce a novel acceleration-fallback cutoff for hierarchical clustering, which adaptively determines the level of granularity. Experiments on three benchmarks (Lap14, Rest14, MAMS) show consistent improvements over strong graph baselines, with substantial gains when paired with RoBERTa backbones. These results position dynamic hypergraph construction as an efficient, powerful alternative for ABSA, with potential extensions to other short-text NLP tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。