GHI: Graphormer over Conditioned Hypergraph Incidence for Aspect-Based Sentiment Analysis

2026-05-21

AI Summary

This work addresses the challenge of precisely aligning sentiment evidence with target aspects in aspect-based sentiment analysis by proposing a conditional hypergraph relational representation framework. It introduces a hypergraph reasoning layer grounded in bipartite graph topology, unifying linguistic and semantic evidence through token–hyperedge associations and leveraging Graphormer for efficient aggregation. Despite employing only 247 million parameters, the model consistently outperforms existing approaches across six standard ABSA benchmarks, achieving performance on par with the 11-billion-parameter Flan-T5. Furthermore, it demonstrates exceptional robustness on both SemEval tasks and the ARTS adversarial dataset.

Abstract

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.

Problem

• Aspect-Based Sentiment Analysis
• Structural Reasoning
• Fine-Grained Sentiment Analysis
• Hypergraph Incidence
• Token-Hyperedge Relations

Innovation

• Graphormer
• hypergraph incidence
• structural reasoning
• aspect-based sentiment analysis
• bipartite topology