EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

External-knowledge enhanced dual encoder and contrastive learning for aspect sentiment triplet extraction

Yuan Huang, Xiaozheng Zhou iD, Ruizhi Yin, Pengwei Shi

PLOS One · 12.03.2026 · 21 (3) · e0340792

DOI: 10.1371/journal.pone.0340792 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 12.03.2026. Verfasst von Yuan Huang und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Information and Electrical Engineering, Hebei University of Engineering, Handan, Hebei, China. Hauptthemen laut MEDLINE: Semantics, Sentiment Analysis. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aspect Sentiment Triplet Extraction (ASTE) is an emerging subtask of Aspect-Based Sentiment Analysis (ABSA), aiming to extract aspect terms, opinion terms, and the corresponding sentiment polarity from sentences. Many existing ASTE methods neglect to mine the deeper semantics of the sentence as well as ignore the intrinsic meanings of individual words. In order to address these limitations, this paper proposes a novel approach for ASTE. Firstly, dual encoders are used to extract the semantic and syntactic information of the sentence, the semantic encoder uses BERT and Graph Convolutional Networks (GCNs) to extract the semantic information, and the syntactic encoder employs a Bi-directional Long and Short-Term Memory (Bi-LSTM) network and GCNs to extract the syntactic information. Secondly, a feature fusion module is designed to fuse the information from the dual encoders. Finally, to enhance the ability of the model to recognize boundary tags, we design a boundary-aware contrastive learning module. Experimental results on ASTE-Data-V1 and ASTE-Data-V2 demonstrate the effectiveness of our proposed method.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SemanticsSentiment AnalysisLong Short Term MemoryConvolutional Neural NetworksGraph Neural Networks

Autor:innen und Institutionen

  • School of Information and Electrical Engineering, Hebei University of Engineering, Handan, Hebei, China.

ORCID-Profile: Xiaozheng Zhou

Zitieren

APA

Huang, Y., Zhou, X., Yin, R., & Shi, P. (2026). External-knowledge enhanced dual encoder and contrastive learning for aspect sentiment triplet extraction. PLOS One, 21(3), e0340792. https://doi.org/10.1371/journal.pone.0340792

Vancouver

Huang Y, Zhou X, Yin R, Shi P. External-knowledge enhanced dual encoder and contrastive learning for aspect sentiment triplet extraction. PLOS One. 2026;21(3):e0340792. doi:10.1371/journal.pone.0340792

BibTeX
@article{Huang2026,
  author = {Huang, Yuan and Zhou, Xiaozheng and Yin, Ruizhi and Shi, Pengwei},
  title = {External-knowledge enhanced dual encoder and contrastive learning for aspect sentiment triplet extraction},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {3},
  pages = {e0340792},
  doi = {10.1371/journal.pone.0340792}
}
Kostenlos starten →