Assessment of the Translation and Post-editing of Machine Translation (MT) with Special Reference to Chinese-English Translation

Wei WANG, Weihong ZHOU

Abstract


The current research reports the real performance of machine translation engines (DeepL and GPT-3.5) in translating Classical Chinese into Modern English as well as the post-editing quality of GPT-3.5. The statistical data reveals that: 1) machine translation saves more time and processing energy than human translators; 2) GPT-3.5’s performance in Chinese-English translation is better than Deepl, and it has the advantage of post-editing and self-evolution; 3) Human translators’ ability of semantic processing is superior than DeepL and GPT-3.5. Thus human translators and machine translation engines shall have a good cooperation in improving the accuracy, comprehensibility and fluency of translated texts.


Keywords


translation; post-editing; GPT-3.5; cooperation

Full Text:

PDF

References


Brown, P. F., Della Pietra, S. A., Della Pietra, V. J., & Mercer, R. L. (1993). The mathematics of statistical machine translation: Parameter estimation. Computational Linguistics, 19(2), 262-311.

Cho, K., van Merrienboer, B., Bahdanau, D., & Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. CoRR, abs/1409.1259.

Hu, K., & Cadwell, P. (2016). A comparative study of post-editing guidelines. Baltic Journal of Modern Computing, 4(2), 346-353.

Johnson, M., Schuster, M., Le, Q. V., Kirkun, M., Wu, Y., Chen, Z., ... Dean, J. (2016). Google’s multilingual neural machine translation system: Enabling zero-shot translation. CoRR, abs/1611.04558.

Koehn, P. (2004). Statistical Machine Translation. Cambridge: Cambridge University Press.

Lample, G., & Conneau, A. (2019). Cross-lingual language model pretraining. CoRR, abs/1901.07291.

O’Brien, S. (2010). Introduction to post-editing: Who, what, how and where to next? Retrieved from http://amta2010.amtaweb.org/AMTA/papers/6-01-ObrienPostEdit.pdf

Och, F. J., & Ney, H. (2003). A systematic comparison of various statistical alignment models. Computational Linguistics, 29(1), 19-51.

Rowda, J. (2016). Better, faster, and more efficient post-editing. Retrieved from http://www.gala-global.org/publication/better-faster-and-more-efficient-post-editing

Wang, W., & Zhou, W. H. (2019). On lengthening and explicitation in the process of translating: An empirical study based on translation tests of MTI students. Higher Education of Social Science, 17(2), 39-46.




DOI: http://dx.doi.org/10.3968/13178

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 Cross-Cultural Communication

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Share us to:   

Remind

We are currently accepting submissions via email only.

The registration and online submission functions have been disabled.

Please send your manuscripts to ccc@cscanada.net，or  ccc@cscanada.org  for consideration. We look forward to receiving your work.

 

 Articles published in Cross-Cultural Communication are licensed under Creative Commons Attribution 4.0 (CC-BY).

 CROSS-CULTURAL COMMUNICATION Editorial Office

Address: 1055 Rue Lucien-L'Allier, Unit #772, Montreal, QC H3G 3C4, Canada.
Telephone: 1-514-558 6138 
Website: Http://www.cscanada.net; Http://www.cscanada.org 
E-mail:caooc@hotmail.com; office@cscanada.net

Copyright © Canadian Academy of Oriental and Occidental Culture