Multilingual Neural Machine Translation for Asian Language Treebank
DOI:
https://doi.org/10.54644/jte.2026.2047Tóm tắt
This study examines multilingual neural machine translation (MNMT) for a diverse group of low-resource Asian languages-Bengali, Filipino, Indonesian, Japanese, Khmer, Malay, and Vietnamese-which differ substantially in linguistic families, writing systems, and typology. This paper evaluates state-of-the-art MNMT systems and introduces a Compact & Language-Sensitive MNMT model designed to improve translation performance while reducing computational cost. The proposed approach shares parameters through a compact multilingual representation, and enhances language discrimination using language-sensitive embeddings, a language-sensitive discriminator, and an adaptive cross-attention mechanism that selects attention parameters based on specific language pairs. Integrated with a multi-stage fine-tuning strategy, this model effectively strengthens cross-lingual transfer while maintaining robust language-specific representations. Experiments on the ALT multi-parallel corpus and the KFTT English-Japanese dataset demonstrate that multilingual models significantly outperform single-language NMT baselines. Despite its smaller size, the proposed Compact & Language-Sensitive MNMT achieves competitive or superior BLEU scores compared to Google’s MNMT, confirming the effectiveness of guided parameter sharing and language-sensitive training. These results highlight the value of compact multilingual architectures and multi-parallel datasets for advancing low-resource Asian machine translation.
Lượt tải
Tài liệu tham khảo
[1] R. Dabre, T. Nakagawa, and H. Kazawa, “A survey of multilingual neural machine translation,” ACM Comput. Surv., vol. 53, no. 5, pp. 1–38, 2020.
[2] D. Bahdanau, K. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” in Proc. Int. Conf. Learn. Representations (ICLR), San Diego, CA, USA, 2015.
[3] M. Ü. Uyar, “RNNs with attention for machine translation,” in Machine Learning and AI with Simple Python and Matlab Scripts: Courseware for Non-computing Majors. Hoboken, NJ, USA: IEEE-Wiley, 2025, pp. 209–223, doi: 10.1002/9781394294985.ch13.
[4] I. Sutskever, O. Vinyals, and Q. V. Le, “Sequence to sequence learning with neural networks,” in Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 27, 2014, pp. 3104–3112.
[5] K. Cho, B. van Merriënboer, D. Bahdanau, and Y. Bengio, “On the properties of neural machine translation: Encoder–decoder approaches,” arXiv preprint, arXiv:1409.1259, 2014.
[6] A. Li, “Application of convolution neural network algorithm in English translation,” in Proc. Int. Conf. Integrated Intelligence and Communication Systems (ICIICS), Kalaburagi, India, 2023, pp. 1–8, doi: 10.1109/ICIICS59993.2023.10421570.
[7] A. Vaswani et al., “Attention is all you need,” in Adv. Neural Inf. Process. Syst. (NeurIPS), 2017, pp. 5998–6008.
[8] Y. Chen, Y. Liu, Y. Cheng, and V. O. K. Li, “A teacher–student framework for zero-resource neural machine translation,” in Proc. 55th Annu. Meeting Assoc. Comput. Linguistics (ACL), Vancouver, BC, Canada, 2017, pp. 1925–1935, doi: 10.18653/v1/P17-1176.
[9] Y. Chen, Y. Liu, and V. O. K. Li, “Zero-resource neural machine translation with multi-agent communication game,” in Proc. AAAI Conf. Artif. Intell., 2018, pp. 5086–5093.
[10] Y. Cheng, Q. Yang, Y. Liu, M. Sun, and W. Xu, “Joint training for pivot-based neural machine translation,” in Proc. Int. Joint Conf. Artif. Intell. (IJCAI), Melbourne, VIC, Australia, 2017, pp. 3974–3980, doi: 10.24963/ijcai.2017/555.
[11] O. Firat, K. Cho, and Y. Bengio, “Multi-way, multilingual neural machine translation with a shared attention mechanism,” in Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Human Lang. Technol. (NAACL-HLT), San Diego, CA, USA, 2016, pp. 866–875, doi: 10.18653/v1/N16-1101.
[12] M. Johnson et al., “Google’s multilingual neural machine translation system: Enabling zero-shot translation,” Trans. Assoc. Comput. Linguistics, vol. 5, pp. 339–351, 2017.
[13] Y. Wang et al., “A compact and language-sensitive multilingual translation method,” in Proc. 57th Annu. Meeting Assoc. Comput. Linguistics (ACL), Florence, Italy, 2019, pp. 1213–1223.
[14] B. Zoph and K. Knight, “Multi-source neural translation,” in Proc. NAACL-HLT, San Diego, CA, USA, 2016, pp. 30–34, doi: 10.18653/v1/N16-1004.
[15] R. Dabre and A. Fujita, “Exploiting multilingualism through multistage fine-tuning for low-resource neural machine translation,” in Proc. Conf. Empirical Methods in Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, Nov. 2019, pp. 1410–1416.
[16] G. Neubig, “The Kyoto free translation task,” 2011. [Online]. Available: http://www.phontron.com/kftt
[17] H. Riza et al., “Introduction of the Asian language treebank,” in Proc. Oriental COCOSDA, 2016.
[18] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in Proc. Int. Conf. Learn. Representations (ICLR), 2015.
[19] K. Papineni, S. Roukos, T. Ward, and W. Zhu, “BLEU: A method for automatic evaluation of machine translation,” in Proc. 40th Annu. Meeting Assoc. Comput. Linguistics (ACL), Philadelphia, PA, USA, 2002.
[20] P. Koehn, “Statistical significance tests for machine translation evaluation,” in Proc. Conf. Empirical Methods in Natural Language Processing (EMNLP), Barcelona, Spain, Jul. 2004.
[21] H. Nguyen et al., “Language-oriented sentiment analysis based on grammar structure and improved self-attention network,” in Proc. 15th Int. Conf. Evaluation of Novel Approaches to Software Engineering (ENASE), Prague, Czech Republic, May 2020, pp. 339–346.
