译前编辑是提高机器翻译质量的重要途径之一,也是人机交互翻译的重要表现。本文旨在探讨基于受控语言的译前编辑对机器翻译(谷歌)的影响,采取iPhone5英语用户手册的汉译作为实验分析对象,研究表明:(1)基于受控语言的译前编辑在充分性与连贯性两大方面都有助于提高谷歌翻译的质量;(2)译前编辑对连贯性的改善程度明显大于对充分性的改善程度;(3)要想生成高质量的译文,只有译前编辑还是远远不够的,还需要译后编辑的参与,两者往往需要联合运用。基于实验与实例本文还提出了一些译前编辑技巧,包括词汇层面、短语层面以及句子层面,对机器翻译的译前编辑实践不无启示。
Pre-editing is an important way to improve the quality of machine translation through machine-human interaction. This paper, taking the Chinese translation of English user manual of iPhone5 as an experimental text, aims to investigate the influence of pre-editing in accordance with controlled language on machine translation (Google). It is found that: 1) pre-editing based on controlled language has a positive influence on the enhancement of both the quality of machine translation regarding adequacy (information content) and fluency of the target text; 2) pre-editing exerts a bigger influence on the improvement of fluency than on adequacy; 3) in order to produce a translated text of high quality, pre-editing itself is far from enough, and thus post-editing is needed to further improve machine translation output. Based on the experiment and example analysis, some pre-editing methods are also put forward in order to give some guidance to pre-editors, including those at lexical, phrasal and sentential levels.
Baker, K.L., A.M. Franz, P.W. Jordan, T. Mitamura & E.H. Nyberg. 1994. Coping with ambiguity in a large-scale machine translation system [A]. In M. Nagao (ed.). Proceedings of the 15th Conference on Computational Linguistics (Volume 1) [C]. New Mexico:Association for Computational Linguistics.90-94.
Cardey, S., P. Greenfield & X. Wu. 2004. Designing a controlled language for the machine translation of medical protocols [A]. In R.E. Frederking & K.B. Taylor (eds.). Machine Translation: From Real Users to Research [C].Heidelberg:Springer.37-47.
Denkowski, M. & A. Lavie. 2010. Meteor-next and the meteor paraphrase tables: Improved evaluation support for five target languages [A]. In C. Burch, P. Koehn, C. Monz, K. Peterson & O. Zaidan (eds.). Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and Metrics [C]. Uppsala Association for Computational Linguistics.339-342.
Mitamura, T., E. Nyberg & E. Torrejon. 1999. Multiple strategies for automatic disambiguation in technical translation [A]. In G. Adriaens (ed.). Proceedings of the 8th International Conference on Theoretical and Methodological Issues in Machine Translation,TMI-99 [C]. Belgium:Kul Centre for Computational Linguistics Leuven.23-25.
Mitamura, T. & E. Nyberg. 1995. Controlled English for knowledge-based MT: Experience with the KANT system [A]. In G. Adriaens (ed.). Proceedings of the 6th International Conference on Theoretical and Methodological Issues in Machine Translation, TMI-95 [C]. Belgium:Kul Centre for Computational Linguistics Leuven.146-147.
Nyberg, E., T. Mitamura & W. Huijsen. 2011. Controlled language for authoring and translation [A]. In H. Somers (ed.). Computers and Translation [C]. Shanghai: Shanghai Foreign Language Education Press.245-281.
Torrejón, E. & C. Rico. 2002. Controlled translation: A new teaching scenario tailor-made for the translation industry [A]. In EAMT (ed.). Proceedings of the 6th EMAT Workshop: Teaching Machine Translation [C]. Belgium:Kul Centre for Centre for Computational Linguistics, UMIST.107-116.
Wojcik R.H.1998. Boeing technical English: An extension of AECMA SE beyond the aircraft maintenance domain[A].In CLAW 98 (ed.). Proceedings of the Second International Workshop on Controlled Language Applications [C]. Pittsburgh:CLAW.137-145.
胡琴琴.2013.汉译英机器翻译译前编辑和译后编辑的效率及质量研究[D].浙江师范大学.
胡清平.2005.机器翻译中的受控语言[J].中国科技翻译(3): 24-27.
刘毅.2014.控制性语言对提高技术规范文本机器翻译质量的实证研究[J].重庆理工大学学报(社会科学版)(3): 96 -101.
魏长宏.2008.机器翻译的译前处理[J].科协论坛(9): 93-94.
吴慧颖.2012.译前编辑与译后编辑分别使用机器翻译的对比——以英国诺里奇市城堡博物馆的荷兰画作简介的翻译为例[J].福建商业高等专科学校学报(10): 101-104.
袁亦宁.2003.受控语言:机器翻译的新途径[J].上海科技翻译(3): 77-80.
