用超图关联结构提升细粒度情感分析的准确性
GHI: Graphormer over Conditioned Hypergraph Incidence for Aspect-Based Sentiment Analysis
- 基于双部超图关联构建统一结构表征接口
- 在6个基准上超越所有基线，247M参数接近110亿参数模型性能
- 小模型仍对复杂数据集保持强鲁棒性，适合资源受限场景
细粒度情感分析要求模型将情感证据与正确方面精准关联，是检验结构化推理能力的理想场景。本文提出GHI框架，基于双部超图关联结构设计一种基于关联关系的结构推理层。该框架将多样化的语言与语义证据表示为词元-超边的关联关系，通过统一接口融合不同结构信号。在6个标准基准上的大量实验表明，GHI在SemEval领域全面优于所有基线；多种子评估显示其稳定优于强模型DeBERTa。进一步实验表明，仅需247M参数，GHI在ISE基准上已接近110亿参数的Flan-T5方法表现。此外，其在挑战性ARTS数据集上表现出强鲁棒性，传统模型性能下降时仍保持高竞争力。结果表明，紧凑的结构推理仍是细粒度任务中对抗规模扩张的有效方案。
原文摘要 · Abstract (English)
Aspect-based sentiment analysis (ABSA) requires models to bind sentiment evidence to the correct aspect, making it a natural testbed for fine-grained structural reasoning. We introduce GHI, a Graphormer-over-Conditioned-Hypergraph-Incidence framework that is designed as an incidence-based structural reasoning layer built on a bipartite topology. GHI represents diverse linguistic and semantic evidence as token--hyperedge incidence relations, allowing different structural signals to be incorporated through a unified interface. Extensive experiments on six standard ABSA benchmarks show that GHI outperforms all baselines on the SemEval domains, and multi-seed evaluations show stable improvements over strong DeBERTa. Further experiments show that with only 247M parameters, GHI approaches the performance of 11B Flan-T5 based methods on the ISE benchmark. Moreover, it demonstrates strong robustness on the challenging ARTS datasets, maintaining highly competitive performance where traditional models degrade. These results demonstrate that compact structural reasoning remains a valuable alternative to scale-driven approaches for fine-grained 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。