计算机科学论文摘要的机翻错误类型及译后编辑
Machine Translation Error Classification and Post Editing for Paper Abstracts in Computer Science
DOI: 10.12677/ml.2024.12111062, PDF,   
作者: 王 宇：大连理工大学外国语学院，辽宁 大连；付茜雯：广州华商学院外国语学院，广东 广州
关键词: 机器翻译；计算机科技论文摘要；错误类型；译后编辑策略；Machine Translation； Paper Abstracts in Computer Science； Error Classification； Post-Editing Strategies
摘要: 本研究采用定性和定量分析方法，系统归类了计算机科技文本摘要中机器翻译出现的错误，其中不符合中文表达习惯的翻译错误占比最大，其次是术语误译、误译、欠译、漏译、过译以及赘译。本研究发现，长难句、被动语态以及术语翻译是造成机器翻译错误的主要原因。针对源文本的逻辑缜密、语步序固定等特征，本研究针对性地对各类错误类型提出了相应译后编辑策略。
Abstract: By means of quantitative and qualitative research methods, this study systematically classifies the errors in MT-generated computer science abstracts. Results show that unidiomatic translation makes up a relatively significant share, followed by terminology mistranslation, mistranslation, under-translation, omission, over-translation, and addition. Due to the informative and academic text features of source texts, long and complex sentences, passive voice and term translation are the main causes of machine translation errors. In view of the logical organization and sequenced structure of source text requirement, this study puts forward well-directed corresponding post-editing strategies.
文章引用：王宇, 付茜雯. 计算机科学论文摘要的机翻错误类型及译后编辑[J]. 现代语言学, 2024, 12(11): 656-667. https://doi.org/10.12677/ml.2024.12111062

参考文献

[1] Ufnalska, S. (2007) Abstracts of Research Articles: Problems of Translation. European Science Editing, 33, 101-104.
[2] 张克亮. 面向机器翻译的汉英句类及句式格式转换[M]. 郑州: 河南大学出版社, 2007.
[3] 李梅, 朱锡明. 译后编辑自动化的英汉机器翻译新探索[J]. 中国翻译, 2013, 34(4): 83-87.
[4] Groves, M. and Mundt, K. (2015) Friend or Foe? Google Translate in Language for Academic Purposes. English for Specific Purposes, 37, 112-121. [Google Scholar] [CrossRef] 
[5] 冯志伟. 机器翻译与人工智能的平行发展[J]. 外国语(上海外国语大学学报), 2018, 41(6): 35-48.
[6] Jia, Y., Carl, M. and Wang, X. (2019) Post-Editing Neural Machine Translation versus Phrase-Based Machine Translation for English-Chinese. Machine Translation, 33, 9-29. [Google Scholar] [CrossRef] 
[7] Folaron, D. (2014) Sharon O’brien, Laura Winther Balling, Michael Carl, Michel Simard and Lucia Specia: Post-Editing of Machine Translation: Processes and Applications. Machine Translation, 29, 69-76. [Google Scholar] [CrossRef] 
[8] Guerberof Arenas, A. (2014) Correlations between Productivity and Quality When Post-Editing in a Professional Context. Machine Translation, 28, 165-186. [Google Scholar] [CrossRef] 
[9] Koponen, M. and Salmi, L. (2018) Post-Editing Quality: Analysing the Correctness and Necessity of Post-Editor Corrections. Linguistica Antverpiensia, New Series—Themes in Translation Studies, 16, 137-148. [Google Scholar] [CrossRef] 
[10] Guerberof, A. (2008) Productivity and Quality in the Post-Editing of Outputs from Translation Memories and Machine Translation. Localization Focus, 7, 11-21.
[11] 崔启亮, 李闻. 译后编辑错误类型研究——基于科技文本英汉机器翻译[J]. 中国科技翻译, 2015, 28(4): 19-22.
[12] DQF-MQM Error Categories.
https://www.taus.net/data-solutions/dqf-mqm-error-annotation
[13] 范华泉, 冷怀明, 郭建秀. 我国医学期刊论文英文摘要典型错误分析[J]. 中国科技期刊研究, 2004, 15(1): 104-106.
[14] 马雪骢. 简论信息型文本翻译的功能实现[J]. 济南职业学院学报, 2008(4): 52-53, 30.
[15] Zobel, J. (2014) Writing for Computer Science. Springer. [Google Scholar] [CrossRef] 
[16] Lommel, A. (2018) Metrics for Translation Quality Assessment: A Case for Standardising Error Typologies. In: Moorkens, J., Castilho, S., Gaspari, F. and Doherty, S., Eds., Translation Quality Assessment, Springer International Publishing, 109-127. [Google Scholar] [CrossRef]