Research on Methods to Enhance Machine Translation Quality Between Low-Resource Languages and Chinese Based on ChatGPT
DOI:
https://doi.org/10.53469/jssh.2024.06(07).09Keywords:
Low-resource languages, Pivot Translation Technique, Pivot Prompting, Machine translation qualityAbstract
In recent years, machine translation engines have leveraged both traditional statistical models and the newer neural network models, achieving significant improvements in translation quality through the use of large-scale, high-quality corpora. These advancements have led to continuous improvements in translation quality for high-resource languages. However, the translation performance for low-resource languages remains suboptimal, primarily due to the difficulty in obtaining large-scale bilingual parallel corpora necessary for training neural network models. This study aims to enhance machine translation quality for low-resource languages by utilizing large language models, exploring various methods to improve translation quality, and evaluating their effectiveness. Specifically, the research focuses on comparing the effectiveness of these two methods through human evaluation using the Multidimensional Quality Metrics (MQM) framework.
References
Artetxe, M., Labaka, G., Agirre, E., & Cho, K. (2018). Unsupervised Neural Machine Translation. In Proceedings of the International Conference on Learning Representations (ICLR)2018. arXiv:1710.11041 [cs.CL].
Bahdanau, D., Cho, K., & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. Proceedings of the International Conference on Learning Representations (ICLR).
Currey, A., Miceli-Barone, A. V., & Heafield, K. (2017). Copied monolingual data improves low-resource neural machine translation. In Proceedings of the Second Conference on Machine Translation. Retrieved from aclanthology.org
Dewangan, S., Alva, S., Joshi, N., & Bhattacharyya, P. (2021). Experience of neural machine translation between Indian languages. Machine Translation, 35(3-4), 71-99.
González-Rubio, J., Navarro-Cerdán, J. R., & Casacuberta, F. (2013). Dimensionality reduction methods for machine translation quality estimation. Machine Translation, 27(3-4), 281-301.
Haque, R., Liu, C.-H., & Way, A. (2021). Recent advances of low-resource neural machine translation. Machine Translation, 35, 451-474.
Kumar, S., Anastasopoulos, A., Wintner, S., & Tsvetkov, Y. (2021). Machine Translation into Low-resource Language Varieties. In C. Zong, F. Xia, W. Li, & R. Navigli (Eds.), Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) (pp. 110-121). Association for Computational Linguistics.
Lavie, A., & Denkowski, M. J. (2009). The METEOR metric for automatic evaluation of machine translation. Machine Translation, 23(3-4), 105-115.
Liu, C.-H., Karakanta, A., Tong, A. N., Aulov, O., Soboroff, I. M., Washington, J., & Zhao, X. (2020). Introduction to the Special Issue on Machine Translation for Low-Resource Languages. Machine Translation, 35(1), 247-249.
Liu, C.-H., Karakanta, A., Tong, A. N., Aulov, O., Soboroff, I. M., Washington, J., & Zhao, X. (2021). Introduction to the second issue on machine translation for low-resource languages. Machine Translation, 35(1), 1-2.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Jinyue Qi
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
