EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction

Yang Chen iD, Bowen Shi

Entropy · 28.02.2024 · 26 (3) · 210

DOI: 10.3390/e26030210 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 28.02.2024. Verfasst von Yang Chen und 1 weiteren Autor:innen. Beteiligte Einrichtung: State Key Lab of Software Development Environment, Beihang University, Beijing 100191, China. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent years have seen a rise in interest in document-level relation extraction, which is defined as extracting all relations between entities in multiple sentences of a document. Typically, there are multiple mentions corresponding to a single entity in this context. Previous research predominantly employed a holistic representation for each entity to predict relations, but this approach often overlooks valuable information contained in fine-grained entity mentions. We contend that relation prediction and inference should be grounded in specific entity mentions rather than abstract entity concepts. To address this, our paper proposes a two-stage mention-level framework based on an enhanced heterogeneous graph attention network for document-level relation extraction. Our framework employs two different strategies to model intra-sentential and inter-sentential relations between fine-grained entity mentions, yielding local mention representations for intra-sentential relation prediction and global mention representations for inter-sentential relation prediction. For inter-sentential relation prediction and inference, we propose an enhanced heterogeneous graph attention network to better model the long-distance semantic relationships and design an entity-coreference path-based inference strategy to conduct relation inference. Moreover, we introduce a novel cross-entropy-based multilabel focal loss function to address the class imbalance problem and multilabel prediction simultaneously. Comprehensive experiments have been conducted to verify the effectiveness of our framework. Experimental results show that our approach significantly outperforms the existing methods.

Schlagwörter

Stichwörter der Autor:innen

attention mechanismdependency treeentropyheterogeneous graph neural networkrelation extraction

Autor:innen und Institutionen

  • State Key Lab of Software Development Environment, Beihang University, Beijing 100191, China.
  • School of Journalism, Communication University of China, Beijing 100024, China.

ORCID-Profile: Yang Chen

Förderung

  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Chen, Y., & Shi, B. (2024). Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction. Entropy, 26(3), 210. https://doi.org/10.3390/e26030210

Vancouver

Chen Y, Shi B. Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction. Entropy. 2024;26(3):210. doi:10.3390/e26030210

BibTeX
@article{Chen2024,
  author = {Chen, Yang and Shi, Bowen},
  title = {Enhanced Heterogeneous Graph Attention Network with a Novel Multilabel Focal Loss for Document-Level Relation Extraction},
  journal = {Entropy},
  year = {2024},
  volume = {26},
  number = {3},
  pages = {210},
  doi = {10.3390/e26030210}
}
Kostenlos starten →