Effects of Six Neural Machine Translators of the Two Business Major Text Types
DOI:
https://doi.org/10.54691/fhss.v2i6.894Keywords:
Neural Machine Translators; Translation Tips; Translation Comparison.Abstract
This study investigates the effects of six major neural machine translators (NMTs) rendering four texts—E-C and C-E directions for the informative and the vocative. By comparing the errors and inadequacies, I found that western-produced NMTs are better at translating E-C and C-E informative texts, though they cannot render culture-loaded words. Baidu, Youdao, and WeChat are similarly good, yet sometimes with confusing blunders. Overall, QQ is the least satisfactory one. For highly vocative E-C texts, all the machine translators are fiascoes since they can only translate the surface meaning, sometimes even confusingly. For C-E vocative texts, DeepL and Google can produce acceptable sentences but retain every piece of information; Chinese-produced NMTs are better at dealing with culture-loaded words. This paper may provide some translation tips for Chinese researchers, the latest trends in NMT for teachers and researchers of the English language, and some insights for technical personnel.
Downloads
References
Chen, D. Z. Contrastive Linguistics Between Chinese and English [M]. Beijing: Foreign Language Teaching and Research Press, 2011.
Cheng Y., Tu, Z. P., Meng, F. D., Zhai, J. J. and Liu, Y. Towards Robust Neural Machine Translation Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers), pages 1756–1766 Melbourne, Australia, July 15 - 20, 2018.
Deng D. and Xue N. W. Translation Divergences in Chinese–English Machine Translation: An Empirical Investigation. Computational Linguistics, Vol. 43, No. 3, 2016 521-565.
Guo, X. Y. Contemporary Practical Business English Translation [M]. Beijing: University of International Business and Economics Press, 2013.
Hutchins, W. J. and Harold L. Somers An introduction to machine translation Somers. London: Academic Press, 1992.
Kaufman, L. and J. Straus The Blue Book of Grammar and Punctuation Hoboken: Jossey-Bass, 2021.
Liu, J. (2020). Comparing and Analyzing Cohesive Devices of SMT and NMT from Chinese to English: A Diachronic Approach. Open Journal of Modern Linguistics, 10, 765-772. https:// doi. org/ 10. 4236/ ojml.2020.106046.
Liu, M. Q. English Varieties and Translation [M]. 2nd Ed. Beijing: China Translation & Publishing Corporation, 2012.
Munteanu, D.S., Fraser, A., Marcu, D.: Improved machine translation performance via parallel sentence extraction from comparable corpora. Proceedings of the Human Language Technology and North American Association for Computational Linguistics Conference (HLT/NAACL 2004). (2004).
Newmark, P. Approaches to Translation [M]. Shanghai: Foreign Language Education Press, 2001.
Reiss, K. “Text types, translation types and translation assessment”. Trans. A. Chesterman, in A. Chesterman (ed.) (1989), pp. 105–15.
Willims, J. Style: Toward Clarity and Grace [M]. Chicago: The University of Chicago Press, 1990.
Wu Z. L., Wei D. M, Li Z. Y., Yu Z. Z., Shang H. C, Chen X. Y, Guo J. X, Wang M. H., Lei L. Z., Tao S. M., Yang H. and Qin Y. Improved method of combining forward translation and back translation for neural machine translation[J]. Journal of Xiamen University (Natural Science). 2022, 5: 1-8.
Wu, Y. H. et al. 2016. Google’s Neural Machine Translation System: Bridging the gap between human and machine translation [OL]. https://arxiv.org/abs/1609.08144 (accessed 20/10/2021).
Xiao, X. Li, S., Yu, W., Liu, J. and Liu, B. “English-Chinese translation based on an improved SEQ2SEQ model” Computer Engineering and Science, vol. 41, no. 7, pp. 1257–1265, 2019.
Zhao, H. J. and Lin G. B. A study on the corpus context strategies for the missing words in Machine Translation [J]. Foreign Language Teaching and Research (bimonthly). 2022, 55(2): 277-287.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
How to Cite
