EUVIMEDEUVIMED entdecken
Crossref

Syntax-Enhanced Contextual Representation Learning for Complex Relation Extraction via Attention-Guided Graph Network

Jiafeng Suo, Jian Fang, Jie Liu, Mingze Wang, Yang Xiao

Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology · 2026-12 · 50 (12) · 3654-3669

DOI: 10.1177/18758967261457533 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, online erschienen am 04.06.2026. Verfasst von Jiafeng Suo und 4 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Relation Extraction (RE) aims to identify semantic relations between entity pairs in text. Pre-trained language models (PLMs) such as BERT provide strong contextual representations, but they may struggle with long-distance dependencies and irrelevant context because they do not explicitly encode syntactic structure. Dependency graphs can inject structural information, yet many graph-based RE models rely on GCN-style aggregation, which is sensitive to noisy parses and does not always integrate semantic and structural features effectively. In this paper, we propose SE-AGGN, a syntax-enhanced framework that combines PLM semantics with dependency structures in a noise-aware and adaptive manner. We employ a Graph Attention Network (GAT) over dependency graphs to softly weight neighboring nodes and reduce error propagation from unreliable edges. We further introduce a semantic-structure fusion attention module to adaptively integrate contextual representations from PLMs with structural features from the graph encoder. Experiments on SemEval-2010 Task 8 and TACRED show that SE-AGGN consistently outperforms the reproduced and commonly used baselines considered in this work, achieving 90.1 Macro-F1 on SemEval using the official SemEval scorer and 71.2 Micro-F1 on TACRED under the standard TACRED evaluation setting. Additional analyses further demonstrate improved robustness under limited supervision and degraded dependency structures.

Zitieren

APA

Suo, J., Fang, J., Liu, J., Wang, M., & Xiao, Y. (2026). Syntax-Enhanced Contextual Representation Learning for Complex Relation Extraction via Attention-Guided Graph Network. Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, 50(12), 3654-3669. https://doi.org/10.1177/18758967261457533

Vancouver

Suo J, Fang J, Liu J, Wang M, Xiao Y. Syntax-Enhanced Contextual Representation Learning for Complex Relation Extraction via Attention-Guided Graph Network. Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology. 2026;50(12):3654-3669. doi:10.1177/18758967261457533

BibTeX
@article{Suo2026,
  author = {Suo, Jiafeng and Fang, Jian and Liu, Jie and Wang, Mingze and Xiao, Yang},
  title = {Syntax-Enhanced Contextual Representation Learning for Complex Relation Extraction via Attention-Guided Graph Network},
  journal = {Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology},
  year = {2026},
  volume = {50},
  number = {12},
  pages = {3654--3669},
  doi = {10.1177/18758967261457533}
}
Kostenlos starten →