基于语料库的ChatGPT译文与人工译文比较研究  

Corpus-Based Comparative Study on ChatGPT Translation and Human Translation

作　　者：朱玉 ZHU Yu(School of Foreign Languages,Liaoning University of International Business and Economics,Dalian Liaoning 116052)

机构地区：[1]辽宁对外经贸学院外国语学院,辽宁大连116052

出　　处：《长治学院学报》2024年第6期106-113,共8页Journal of Changzhi University

基　　金：辽宁省教育厅面上项目“应急语言服务语境下翻译能力的构建与培养研究”(LJKMR20221882)。

摘　　要：文章以人工译者和ChatGPT翻译的外交部发言人例行记者会英译本为语料,采用定性和定量的研究方法,从词汇、句式和篇章三个层面对比两个译文的特点。研究结果表明:(1)ChatGPT译文在词汇丰富度和复杂度上略高,但个别词汇的翻译不够准确,而人工译文倾向于使用简洁且准确的词汇。(2)ChatGPT往往保持原文的句法结构,形成较长的复杂句式;人工译者则倾向于将长句拆分为短句,使译文更为简洁。(3)ChatGPT通过频繁的名词化展现原文的正式性,但在连贯性和流畅性上稍逊于人工译文;人工译者通过灵活使用连词和代词,增强了译文的可读性。此外,文章还剖析了两个译文差异的成因,对如何有效利用ChatGPT进行翻译具有参考意义。This paper examines the translation characteristics of the Foreign Ministry Spokesperson’s Regular Press Conference translations from human translators and ChatGPT,employing both qualitative and quantitative research methods.The analysis,focusing on lexical,syntactic,and textual levels,reveals that ChatGPT’s translations possess a richer and more complex vocabulary.However,ChatGPT sometimes struggles with the precision of specific terms,unlike human translators who consistently select concise and accurate vocabulary.Additionally,ChatGPT tends to maintain the original syntactic structures,resulting in longer and more complex sentences,while human translators often split long sentences for clarity.ChatGPT’s translations also display a notable formality of the source text,marked by frequent nominalization,but they fall slightly behind in coherence and fluency,while human translators enhance the readability of translations through the flexible use of conjunctions and pronouns.The paper further delves into the reasons behind these differences,providing valuable insights into the effective use of ChatGPT for translation tasks.

关 键 词：ChatGPT翻译 人工翻译 语料库 翻译特点 

分 类 号：H059[语言文字—语言学]