Transformer-Based Re-Ranking Model for Enhancing Contextual and Syntactic Translation in Low-Resource Neural Machine Translation
Electronics · 08.01.2025 · 14 (2) · 243
DOI: 10.3390/electronics14020243 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 08.01.2025. Verfasst von Arifa Javed und 7 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan.
Abstract (Originalsprache)
Neural machine translation (NMT) plays a vital role in modern communication by bridging language barriers and enabling effective information exchange across diverse linguistic communities. Due to the limited availability of data in low-resource languages, NMT faces significant translation challenges. Data sparsity limits NMT models’ ability to learn, generalize, and produce accurate translations, which leads to low coherence and poor context awareness. This paper proposes a transformer-based approach incorporating an encoder–decoder structure, bilingual curriculum learning, and contrastive re-ranking mechanisms. Our approach enriches the training dataset using back-translation and enhances the model’s contextual learning through BERT embeddings. An incomplete-trust (in-trust) loss function is introduced to replace the traditional cross-entropy loss during training. The proposed model effectively handles out-of-vocabulary words and integrates named entity recognition techniques to maintain semantic accuracy. Additionally, the self-attention layers in the transformer architecture enhance the model’s syntactic analysis capabilities, which enables better context awareness and more accurate translations. Extensive experiments are performed on a diverse Chinese–Urdu parallel corpus, developed using human effort and publicly available datasets such as OPUS, WMT, and WiLi. The proposed model demonstrates a BLEU score improvement of 1.80% for Zh→Ur and 2.22% for Ur→Zh compared to the highest-performing comparative model. This significant enhancement indicates better translation quality and accuracy.
Förderung
- Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan
Zitieren
APA
Javed, A., Zan, H., Mamyrbayev, O., Abdullah, M., Ahmed, K., Oralbekova, D., Dinara, K., & Akhmediyarova, A. (2025). Transformer-Based Re-Ranking Model for Enhancing Contextual and Syntactic Translation in Low-Resource Neural Machine Translation. Electronics, 14(2), 243. https://doi.org/10.3390/electronics14020243
Vancouver
Javed A, Zan H, Mamyrbayev O, Abdullah M, Ahmed K, Oralbekova D, et al. Transformer-Based Re-Ranking Model for Enhancing Contextual and Syntactic Translation in Low-Resource Neural Machine Translation. Electronics. 2025;14(2):243. doi:10.3390/electronics14020243
BibTeX
@article{Javed2025,
author = {Javed, Arifa and Zan, Hongying and Mamyrbayev, Orken and Abdullah, Muhammad and Ahmed, Kanwal and Oralbekova, Dina and Dinara, Kassymova and Akhmediyarova, Ainur},
title = {Transformer-Based Re-Ranking Model for Enhancing Contextual and Syntactic Translation in Low-Resource Neural Machine Translation},
journal = {Electronics},
year = {2025},
volume = {14},
number = {2},
pages = {243},
doi = {10.3390/electronics14020243}
}
EUVIMED