依存语法视角下人工翻译和机器翻译的句法特征对比研究——以学术文本为例
A Comparative Study of Syntactic Features between Human Translations and Machine Translations from a Dependency Grammar Perspective—A Case Study of Academic Texts
摘要: 本研究基于依存语法理论，聚焦平均依存距离和支配词居后的依存关系占比两项指标，对比分析了汉语学术文本的人工、谷歌翻译及ChatGPT-4o的三个英译本句法特征。研究发现，人工译本与ChatGPT-4o译本在平均依存距离上无显著差异，且两者均低于谷歌翻译译本，这表明ChatGPT-4o能通过缩短依存距离降低认知负荷；此外，ChatGPT-4o译本在处理中等长度句子时，其支配词居后的依存关系占比小于其他两类翻译文本，这说明ChatGPT-4o译本在处理中等长度句子时更倾向于减少读者的认知负荷。从以上两点看ChatGPT-4o用于翻译能减少译本的句法复杂度，从而提高了译文质量。
Abstract: Based on dependency grammar theory, this study, focusing on two key indicators: the mean dependency distance and the percentage of head-final dependency relations, comparatively analyzes the syntactic features of Chinese academic texts’ three English translation versions: human-translated, Google Translate-translated, and ChatGPT-4o-translated texts. The findings reveal that there is no significant difference in the mean dependency distance between human and ChatGPT-4o translations, and both demonstrate lower values compared to the translated texts of Google Translate, indicating that ChatGPT-4o can reduce readers’ cognitive load by shortening syntactic dependency distance. Additionally, when translating medium-length sentences, ChatGPT-4o translations exhibit a smaller proportion of head-final dependency relations than the other two versions, suggesting its tendency to minimize readers’ cognitive effort. These findings suggest that applying ChatGPT-4o to translation can reduce the syntactic complexity and improve the translation quality.
文章引用：张雨洁. 依存语法视角下人工翻译和机器翻译的句法特征对比研究——以学术文本为例[J]. 现代语言学, 2025, 13(7): 491-498. https://doi.org/10.12677/ml.2025.137734

参考文献

[1] Toury, G. (1979) Interlanguage and Its Manifestations in Translation. Meta, 24, 223-231.
[2] Frawley, W. (1984) Prolegomenon to a Theory of Translation. In: Frawley, W., Ed., Translation: Literary, Linguistic, and Philosophical Perspectives, Associated University Presses, 159-175.
[3] Trosborg, A. (1997) Translating Hybrid Political Texts. In: Trosborg, A., Ed., Text Typology and Translation, John Benjamins Publishing Company, 145-159.
[4] Kruger, H. and Van Rooy, B. (2016) Constrained Language: A Multidimensional Analysis of Translated English and a Non-Native Indigenised Variety of English. English World-Wide, 37, 26-57.
[5] 范璐, 蒋跃. 翻译语言特征新假设“折中假设”——基于依存语法的计量研究[J]. 外语教学与研究, 2024, 56(1): 136-147+161.
[6] Tesnière, L. (2015) Elements of Structural Syntax. John Benjamins Publishing Company.
[7] Bizzoni, Y., Juzek, T.S., España-Bonet, C., Dutta Chowdhury, K., Van Genabith, J. and Teich, E. (2020) How Human Is Machine Translationese? Comparing Human and Machine Translations of Text and Speech. Proceedings of the 17th International Conference on Spoken Language Translation, Online, 9-10 July 2020, 280-290.
[8] Peng, R., Hao, T. and Fang, Y. (2021) Syntax-Aware Neural Machine Translation Directed by Syntactic Dependency Degree. Neural Computing and Applications, 2, 1-17.
[9] Fan, L. and Jiang, Y. (2019) Can Dependency Distance and Direction Be Used to Differentiate Translational Language from Native Language? Lingua, 224, 51-59.
[10] 蒋跃, 范璐, 王余蓝. 基于依存树库的翻译语言句法特征研究[J]. 外语教学, 2021, 42(3): 41-46.
[11] 耿芳, 胡健. 人工智能辅助译后编辑新方向——基于ChatGPT的翻译实例研究[J]. 中国外语, 2023(3): 41-47.
[12] Chomsky, N. (1957) Syntactic Structures. Mouton & Co.
[13] Imrényi, A. and Mazziotta, N. (2020) Chapters of Dependency Grammar: A Historical Survey from Antiquity to Tesnière. John Benjamins Publishing Company.
[14] 刘海涛. 依存关系与语言网络[M]. 北京: 科学出版社, 2022: 9.
[15] Temperley, D. (2007) Minimization of Dependency Length in Written English. Cognition, 105, 300-333.
[16] Liu, H. (2008) Dependency Distance as a Metric of Language Comprehension Difficulty. Journal of Cognitive Science, 9, 159-191.
[17] Zhang, G. and Liu, H. (2019) A Quantitative Analysis of English Variants Based on Dependency Treebanks. Glottometrics, 44, 16-33.
[18] Hudson, R. (2010) An Introduction to Word Grammar. Cambridge University Press.
[19] Gibson, E. (1998) Linguistic Complexity: Locality of Syntactic Dependencies. Cognition, 68, 1-76.
[20] Liang, J., Fang, Y., Lv, Q. and Liu, H. (2017) Dependency Distance Differences across Interpreting Types: Implications for Cognitive Demand. Frontiers in Psychology, 8, Article 2132.
[21] Jiang, X. and Jiang, Y. (2020) Effect of Dependency Distance of Source Text on Disfluencies in Interpreting. Lingua, 243, Article 102873.
[22] Shen, M., Lin, Y., Lv, Q. and Liang, J. (2023) A Corpus-Based Analysis of the Effect of Syntactic Complexity on Disfluency in Consecutive Interpreting. Lingua, 291, Article 103562.
[23] Liu, H. (2010) Dependency Direction as a Means of Word-Order Typology: A Method Based on Dependency Treebanks. Lingua, 120, 1567-1578.
[24] 沈梦菲, 黄伟. 寻找机器翻译痕迹——神经机器翻译文本的句法特征研究[J]. 外语教学与研究, 2024(3): 429-441+480-481.
[25] Jiao, W., Wang, W., Huang, J., Wang, X., Shi, S. and Tu, Z. (2023) Is ChatGPT a Good Translator? Yes with GPT-4 as the Engine.
http://arxiv.org/abs/2301.08745
[26] Jiang, J. and Liu, H. (2015) The Effects of Sentence Length on Dependency Distance, Dependency Direction and the Implications-Based on a Parallel English-Chinese Dependency Treebank. Language Sciences, 50, 93-104.
[27] Yngve, V. (1960) A Model and a Hypothesis for Language Structure. Proceedings of the American Philosophical Society, 104, 444-466.
[28] Niu, R. and Liu, H. (2022) Effects of Syntactic Distance and Word Order on Language Processing: An Investigation Based on a Psycholinguistic Treebank of English. Journal of Psycholinguistic Research, 51, 1043-1062.