Concept-aware contrastive representation learning for cross-translation semantic consistency modeling of the Analects
PLOS One · 2026
DOI: 10.1371/journal.pone.0358227 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Tang He und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Foreign Language Faculty, Chizhou University, Chizhou, China. Hauptthemen laut MEDLINE: Semantics, Translating, Language. Die Arbeit nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Excellent Scientific Research and Innovation Team of Anhui Colleges, Key Research Projects of Universities in Anhui Province, Industry-University Cooperative Education Project by the Ministry of Education.
Abstract (Originalsprache)
As a representative Chinese classical text, the Analects has been translated into English in many versions over a long historical period, and different translators show substantial variation in concept rendering and language style. To address the lack of a quantifiable and reproducible framework for comparing semantic consistency across multiple English translations of the Analects , this paper proposes a concept-aware semantic consistency modeling framework for cross-translation comparison. The proposed method first constructs a unified parallel corpus input based on sentence groups aligned by chapter and sentence IDs. It then introduces concept-term normalization and proper-name normalization to reduce surface lexical variation across translations. In addition, it combines a shared sentence encoder, supervised contrastive learning, and concept-aware constraints to learn sentence representations with cross-translation consistency. Based on the learned representations, the framework is evaluated through two primary tasks, namely cross-translation retrieval and low-consistency detection. Experimental results show that, within the five-translation dataset examined in this study, the proposed method achieves the strongest overall performance across the evaluated settings. The Full model achieves R@1 = 0.936 and F1 = 0.807. The supplementary association analysis further shows that higher model scores tend to be associated with translation pairs labeled as high consistency. These findings support the framework as a computational aid for cross-translation comparison and for identifying translation pairs that may warrant closer expert examination, rather than as a general-purpose method for automatic translation-quality assessment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Foreign Language Faculty, Chizhou University, Chizhou, China.
- School of Big Data and Artificial Intelligence, Chizhou University, Chizhou, China.
- BNRist, Tsinghua University, Beijing, China.
- School of Cyber Science and Engineering, Ningbo University of Technology, Ningbo, China.
ORCID-Profile: Peng Dai
Förderung
- Excellent Scientific Research and Innovation Team of Anhui Colleges
- Key Research Projects of Universities in Anhui Province
- Industry-University Cooperative Education Project by the Ministry of Education
- the High-level Talent Research Start-up Fund of Chizhou University
- 2023 China University Industry University Research Innovation Fund-Digital Intelligence Science and Education Project
- Key Humanities Research Project of Chizhou University
Zitieren
APA
He, T., Dai, P., Wang, R., Zhao, Y., & Zhao, C. (2026). Concept-aware contrastive representation learning for cross-translation semantic consistency modeling of the Analects. PLOS One. https://doi.org/10.1371/journal.pone.0358227
Vancouver
He T, Dai P, Wang R, Zhao Y, Zhao C. Concept-aware contrastive representation learning for cross-translation semantic consistency modeling of the Analects. PLOS One. 2026. doi:10.1371/journal.pone.0358227
BibTeX
@article{He2026,
author = {He, Tang and Dai, Peng and Wang, Rong and Zhao, Yanyang and Zhao, Chen},
title = {Concept-aware contrastive representation learning for cross-translation semantic consistency modeling of the Analects},
journal = {PLOS One},
year = {2026},
doi = {10.1371/journal.pone.0358227}
}
EUVIMED