{"ID":2875312,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.02033","arxiv_id":"2509.02033","title":"StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matching","abstract":"Text semantic matching requires nuanced understanding of both structural relationships and fine-grained semantic distinctions. While pre-trained language models excel at capturing token-level interactions, they often overlook hierarchical structural patterns and struggle with subtle semantic discrimination. In this paper, we proposed StructCoh, a graph-enhanced contrastive learning framework that synergistically combines structural reasoning with representation space optimization. Our approach features two key innovations: (1) A dual-graph encoder constructs semantic graphs via dependency parsing and topic modeling, then employs graph isomorphism networks to propagate structural features across syntactic dependencies and cross-document concept nodes. (2) A hierarchical contrastive objective enforces consistency at multiple granularities: node-level contrastive regularization preserves core semantic units, while graph-aware contrastive learning aligns inter-document structural semantics through both explicit and implicit negative sampling strategies. Experiments on three legal document matching benchmarks and academic plagiarism detection datasets demonstrate significant improvements over state-of-the-art methods. Notably, StructCoh achieves 86.7% F1-score (+6.2% absolute gain) on legal statute matching by effectively identifying argument structure similarities.","short_abstract":"Text semantic matching requires nuanced understanding of both structural relationships and fine-grained semantic distinctions. While pre-trained language models excel at capturing token-level interactions, they often overlook hierarchical structural patterns and struggle with subtle semantic discrimination. In this pap...","url_abs":"https://arxiv.org/abs/2509.02033","url_pdf":"https://arxiv.org/pdf/2509.02033v1","authors":"[\"Chao Xue\",\"Ziyuan Gao\"]","published":"2025-09-02T07:21:36Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Language Model\"]","has_code":false}