EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

RSTGP: A Relation-Aware and Span-Graph-Enhanced Method for Joint Entity and Relation Extraction from Medical Texts

Faguo Zhou, Shuyu Yao, Yi Wu, Zhe You, Jianshen Yang, Kaile Lyu, Menglin Chen

Applied Sciences · 22.04.2026 · 16 (9) · 4102

DOI: 10.3390/app16094102 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 22.04.2026. Verfasst von Faguo Zhou und 6 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electronic health records (EHRs) contain abundant medical entities and relations, and their accurate extraction is essential for medical knowledge graph construction and clinical decision-support. However, medical texts are typically characterized by dense terminology, syntactically complex expressions, and frequent overlapping triplets, which significantly increase the difficulty of joint extraction. Although table-filling methods such as GPLinker have achieved strong performance, they remain limited in modeling cross-relation interactions, capturing latent structural dependencies among candidate spans, and reducing noise from redundant entity-pair combinations. To address these limitations, we propose RSTGP, a unified joint extraction framework built upon the GPLinker paradigm. The proposed framework integrates three key mechanisms: (1) a relation-aware scoring strategy that enhances cross-relation interaction and calibrates relation scores; (2) a span-level graph enhancement mechanism that captures latent structural dependencies among candidate spans; and (3) a type-constrained calibration mechanism that suppresses implausible subject–object combinations. Extensive experiments on the CMeIE and DuIE2.0 datasets demonstrate that RSTGP consistently outperforms seven representative baseline models and achieves F1 scores of 62.75% and 76.79%, respectively. In particular, the proposed model shows clear advantages in handling overlapping and multiple triplets, yielding a more robust performance in complex extraction scenarios.

Förderung

  • National Key Research and Development Program of China

Zitieren

APA

Zhou, F., Yao, S., Wu, Y., You, Z., Yang, J., Lyu, K., & Chen, M. (2026). RSTGP: A Relation-Aware and Span-Graph-Enhanced Method for Joint Entity and Relation Extraction from Medical Texts. Applied Sciences, 16(9), 4102. https://doi.org/10.3390/app16094102

Vancouver

Zhou F, Yao S, Wu Y, You Z, Yang J, Lyu K, et al. RSTGP: A Relation-Aware and Span-Graph-Enhanced Method for Joint Entity and Relation Extraction from Medical Texts. Applied Sciences. 2026;16(9):4102. doi:10.3390/app16094102

BibTeX
@article{Zhou2026,
  author = {Zhou, Faguo and Yao, Shuyu and Wu, Yi and You, Zhe and Yang, Jianshen and Lyu, Kaile and Chen, Menglin},
  title = {RSTGP: A Relation-Aware and Span-Graph-Enhanced Method for Joint Entity and Relation Extraction from Medical Texts},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {9},
  pages = {4102},
  doi = {10.3390/app16094102}
}
Kostenlos starten →