The Application of Machine Translation in Informative Text
Abstract
unparalleled efficiency, producing huge social and economic benefits. While the quality of machine translation has significantly improved, errors still persist in the output. This study takes an excerpt from Flight, the Complete History of Aviation as an example, employs a case study
method and chooses Google Translate to pre-translate the source text on the YiCAT platform. By contrasting the machine-translated output
with Post-editing version, the study analyzes utilization efficiency of MT outputs and common errors of MT results. A total of four major error
types are identified. The study also summarizes the corresponding post-editing strategies for different types of machine translation errors, aiming to provide insights for English-Chinese translation of informative texts.
Keywords
Full Text:
PDFReferences
[1] Newmark, P. A Textbook of Translation[M]. Shanghai: Shanghai Foreign Language Education Press, 2001.
[2] Translation Automation User Society. TAUS Machine Translation Market Report 2017[R]. De Rijp: Translation Automation User Society, 2017.
[3] Translators Association of China. China Translation Industry Development Report[R]. 2023:41.
[4] Yonghui Wu, Mike Schuster, Zhifeng Chen, et al. Google's Neural Machine Translation System: Bridging the Gap between Human and
Machine Translation.
[5] Limei, Zhu Ximing. Error Patterns and Statistical Analyses of an English-Chinese Machine Translation Corpus[J]. Journal of University of Shanghai for Science and Technology(Social Sciences Edition). 35.03(2013): 201-207.
[6] Hu Chuan-cheng, Jiang Hui. Research on the Application of Machine Translation in Chinese-Uighur Translation Teaching[J]. Journal of
Kashi University. 2025(4): 46.
DOI: http://dx.doi.org/10.70711/rcha.v3i8.7945
Refbacks
- There are currently no refbacks.
