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

TL;DR

GHI introduces a hypergraph-based structural reasoning framework for aspect-based sentiment analysis, outperforming baselines and scaling efficiently with fewer parameters.

Contribution

It presents a novel incidence-based hypergraph reasoning layer integrated with Graphormer for improved ABSA performance.

Findings

GHI outperforms all baselines on six ABSA benchmarks.

Achieves near state-of-the-art with only 247M parameters.

Demonstrates robustness on challenging datasets.

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.