EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improving low-resource neural machine translation by semantic distance augmentation

Fuxue Li, Hong Yan, Chuncheng Chi, Peijun Xie, Shilin Zhang, Xingyue Li

PeerJ Computer Science · 28.07.2026 · 12 · e4056

DOI: 10.7717/peerj-cs.4056 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 28.07.2026. Verfasst von Fuxue Li und 5 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yingkou Center for Technical Support and Verification of New Quality Productive Forces, The Scientific Research Foundation of Liaoning Province, The Natural Science Foundation of Liaoning Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural machine translation (NMT) has witnessed substantial advancements, leveraging its learning capability to deliver highly accurate translations. Nevertheless, the efficacy of NMT models is contingent upon the accessibility of extensive-scale, high-quality training data, and its performance suffers notably in the absence of such datasets. To tackle this challenge, we propose a semantic distance augmentation (SDA) method that integrates syntactic information from constituency parse trees into the NMT encoder to optimize self-attention. Specifically, the source language sentences in the training set are analyzed by constituency parse analysis and the semantic distance attention matrix is constructed. Then, a fusion strategy is designed to integrate this matrix into the self-attention weight, enhancing the representation of the source sentences. In addition, a SDA length-aware strategy is proposed to adaptively control the contribution of semantic distance in the attention computation. Empirical evaluations across multiple low-resource language pairs reveal that the SDA method achieves statistically significant improvements in translation quality over the strong baseline, without requiring additional training data or increasing model complexity.

Förderung

  • Yingkou Center for Technical Support and Verification of New Quality Productive Forces
  • The Scientific Research Foundation of Liaoning Province
  • The Natural Science Foundation of Liaoning Province
  • The Project of Yingkou Institute of Technology
  • The Foundation of Yingkou Automation Industrial Control Professional Technology Innovation Center

Zitieren

APA

Li, F., Yan, H., Chi, C., Xie, P., Zhang, S., & Li, X. (2026). Improving low-resource neural machine translation by semantic distance augmentation. PeerJ Computer Science, 12, e4056. https://doi.org/10.7717/peerj-cs.4056

Vancouver

Li F, Yan H, Chi C, Xie P, Zhang S, Li X. Improving low-resource neural machine translation by semantic distance augmentation. PeerJ Computer Science. 2026;12:e4056. doi:10.7717/peerj-cs.4056

BibTeX
@article{Li2026,
  author = {Li, Fuxue and Yan, Hong and Chi, Chuncheng and Xie, Peijun and Zhang, Shilin and Li, Xingyue},
  title = {Improving low-resource neural machine translation by semantic distance augmentation},
  journal = {PeerJ Computer Science},
  year = {2026},
  volume = {12},
  pages = {e4056},
  doi = {10.7717/peerj-cs.4056}
}
Kostenlos starten →