Recognition and Processing Strategies for colloquial and literary readings in Machine Translation: Taking Southern Fujian Dialect as an Example

Jinming Liu

doi:10.62051/ijcsit.v4n2.04

Authors

Jinming Liu

DOI:

https://doi.org/10.62051/ijcsit.v4n2.04

Keywords:

Neural Machine Translation (NMT), Southern Fujian Dialect, Chinese dialects

Abstract

This study addresses the challenges of Neural Machine Translation (NMT) in handling textual and colloquial discrepancies in Chinese dialects, using Southern Min in Fujian as a case. It highlights the current state of NMT technology and explores sub word representation methods (e.g., Byte Pair Encoding) to mitigate issues with low-frequency and dialectal words. Dynamic attention mechanisms are discussed for their role in recognizing context-specific differences in reading and writing. Transfer learning and fine-tuning of pre-trained models are introduced as optimization strategies, alongside adaptive learning adjustments like dynamic learning rates, to enhance model flexibility and precision in complex linguistic scenarios. This paper offers practical approaches and theoretical insights to improve NMT's performance and adaptability in managing dialectical misreadings.

Downloads

Download data is not yet available.

References

[1] Lin, X.F., Wu, X.F. (2015). Xiamen, Zhangzhou, and Quanzhou Minnan Dialects in the Perspective of Cross Strait Exchange. Southeast Academic, (06), 244-245.

[2] Li, R.L. (1963). The colloquial and literary readings of Xiamen Dielact. Xiamen University(Social Science Edition), (02), 58-59, 95-96.

[3] Chu, C.H., & Wang, R. (2018). A Survey of Domain Adaptation for Neural Machine Translation. Proceedings of the 27th International Conference on Computational Linguistics, 1304-1319.

[4] Raj Dabre, Chu, C.H. & Kunchukuttan, A. (2020). A Comprehensive Survey of Multilingual Neural Machine Translation, 111: 22-23.

[5] Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L. & Polosukhin, I.. (2017). Attention is All You Need. In Advances in Neural information Processing Systems (pp.5998-6008), 2.

[6] 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), 3-4.

[7] Gibadulin., Valeev, A., Khusainova., & Khan, A. (2020). A Survey of Methods to Leverage Monolingual Data in Low-resource Neural Machine Translation, 6-7.

[8] Sennrich, R., Haddow, B, & Birch, A. (2016). Neural Machine Translation of Rare Words with sub word Units. Proceedings of the 54thAnnual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 1715-1725.

[9] Cho, K, Van Merrienboer, B., Gulcehre, Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation, 2-3.

[10] Wu, Y.H., Schuster, M., Chen, Z.F., Le, Q.V., Norouzi, M., Macherey, W et al. (2016). Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation, 2-4.

[11] Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y.Q., Li, W., Liu, P.J.. (2020). Exploring the limits of Transfer Learning with a Unified Text-to-Text Transformer, /ournal of Machine Learning Research, 21(140), 1-67.