Mirror your words, but NOT your wordings: A network approach to human translation and machine translation

Xinyi Huang, Yumeng Lin and Junying Liang
Zhejiang University | Tongji University

Current research has demonstrated the potential of large language models, such as GPT, as powerful translation tools. However, gaps remain in understanding how human and machine translation differ across linguistic and structural levels. This study adopts a network-based approach, using syntactic dependency networks to investigate structural differences in translations produced by humans and machines (Google Translate and ChatGPT). The findings revealed that human translation networks exhibit higher clustering coefficients and shorter average path lengths compared to ChatGPT translations, along with lower density and degree centrality than Google Translate. Human translations also contain fewer function words among central nodes than machine translations. These findings suggest that while machine translation prioritizes producing grammatically well-formed sentences, human translation tends to be more concise and efficient in transmitting information, optimizing the balance between syntactic simplicity and communicative clarity. Machine translation mirrors human words but does not fully replicate the syntactic and structural patterns of human translation. Our study offers new insights for future studies on translation in the context of AI.

Publication history

Date received: 5 February 2025

Date accepted: 6 July 2026

Published online: 30 July 2026

Table of contents

Translation Studies has long examined the human dimensions of translation — agency, creativity, and the role of the translator (Venuti 1995; Toury 2012). The integration of artificial intelligence systems challenges these traditional paradigms by shifting translation from a human-centered to a data-driven practice (House 2014; Pym 2014). In the era of AI, the examination of the differences between human translation and machine translation becomes an imperative subject for exploration, particularly with the emergence of large language models (LLMs) and their immense potential. Recent research has highlighted the potential of LLMs, such as GPT, to function as powerful translation tools, offering a compelling alternative to conventional neural machine translation systems (Jiao et al. 2023; L. Wang et al. 2023; Wu et al. 2024). Specifically, studies by Jiao et al. (2023) and L. Wang et al. (2023) demonstrate that GPT surpasses commercial machine translation systems in both automated metrics and human evaluation. Studies have also highlighted GPT’s ability to rival human translators in certain contexts, achieving comparable performance to junior translators; however, it still lags behind more senior translators in certain quantitative quality scores (e.g., Marshall 2024; Yan et al. 2024).

Full-text access is restricted to subscribers. Log in to obtain additional credentials. For subscription information see Subscription & Price. Direct PDF access to this article can be purchased through our e-platform.

References

Albert, Réka, Hawoong Jeong, and Albert-László Barabási
2000 “Error and Attack Tolerance of Complex Networks.” Nature 406 (6794): 378–382. Google Scholar logo with link to Google Scholar
Barabási, Albert-László, and R. E. Crandall
2002 “Linked: The New Science of Networks.” American Journal of Physics 71(4): 409–410. Google Scholar logo with link to Google Scholar
Barabási, Albert-László, and Réka, Albert
1999 “Emergence of Scaling in Random Networks.” Science 286 (5439): 509–512. Google Scholar logo with link to Google Scholar
Baronchelli, Andrea, Ramon Ferrer-i-Cancho, Romualdo Pastor-Satorras, Nick Chater, and Morten H. Christiansen
2013 “Networks in Cognitive Science.” Trends in Cognitive Sciences 17 (7): 348–360. Google Scholar logo with link to Google Scholar
Cancho, Ramon Ferrer I., and Richard V. Solé
2001 “The Small World of Human Language.” Proceedings of the Royal Society B: Biological Sciences 268 (1482): 2261–2265. Google Scholar logo with link to Google Scholar
Cancho, Ramon Ferrer I., Ricard V. Solé, and Reinhard Köhler
2004 “Patterns in Syntactic Dependency Networks.” Physical Review. E 69 (5): 051915. Google Scholar logo with link to Google Scholar
Čech, Radek, and Ján Mačutek
2009 “Word Form and Lemma Syntactic Dependency Networks in Czech: A Comparative Study.” Glottometrics 19: 85–98.Google Scholar logo with link to Google Scholar
Čech, Radek, Ján Mačutek, and Haitao Liu
2016 “Syntactic Complex Networks and Their Applications.” Understanding Complex Systems: 167–186. Google Scholar logo with link to Google Scholar
Chen, Heng, Xinying Chen, and Haitao Liu
2018 “How Does Language Change as a Lexical Network? An Investigation Based on Written Chinese Word Co-occurrence Networks.” PloS One 13 (2): 1–22. Google Scholar logo with link to Google Scholar
Chen, Xinying, and Haitao Liu
2016 “Function Nodes in Chinese Syntactic Networks.” Understanding Complex Systems 99: 187–201. Google Scholar logo with link to Google Scholar
Chen, Xinying, Chunshan, Xu, and Wenwen, Li
2011 “Extracting Valency Patterns of Word Classes from Syntactic Complex Networks.” In DepLing 2011 Proceedings: International Conference on Dependency Linguistics Depling 2011, Barcelona, September 5–7 2011, edited by Kim Gerdes, Eva Hajičová, and Leo Wanner, 165–172.Google Scholar logo with link to Google Scholar
Chen, Xinying, Haitao Liu, and Kim, Gerdes
2015 “Classifying Syntactic Categories in the Chinese Dependency Network.” In Proceedings of the Third International Conference on Dependency Linguistics Depling 2015, edited by Joakim Nivre and Eva Hajičová, 74–81. Uppsala: Uppsala University.Google Scholar logo with link to Google Scholar
Cheng, Hu
2021 “ ‘Functional Equivalence’ Cases in E–C Translation of Long Sentences in EST Text and Their Implications for Translation Teaching.” Communication Across Borders: Translation & Interpreting 1 (2): 22–28.Google Scholar logo with link to Google Scholar
Choromański, Krzysztof, Michał Matuszak, and Jacek MiȩKisz
2013 “Scale-Free Graph with Preferential Attachment and Evolving Internal Vertex Structure.” Journal of Statistical Physics 151 (6): 1175–1183. Google Scholar logo with link to Google Scholar
Cong, Jin, and Haitao Liu
2014 “Approaching Human Language with Complex Networks.” Physics of Life Reviews 11 (4): 598–618. Google Scholar logo with link to Google Scholar
Corpas Pastor, Gloria, and Laura Noriega-Santiáñez
2024 “Human versus Neural Machine Translation Creativity: A Study on Manipulated MWEs in Literature.” Information 15 (9): 530. Google Scholar logo with link to Google Scholar
Cui, Xinru, Jinxu Qi, Hao Tan, and Feng Chen
2017 “Comparison of Ancient and Modern Chinese Based on Complex Weighted Networks.” PloS One 12 (11): 1–14. Google Scholar logo with link to Google Scholar
De Marneffe, Marie-Catherine, Bill MacCartney, and Christopher D. Manning
2006 “Generating Typed Dependency Parses from Phrase Structure Parses.” Language Resources and Evaluation: 449–454.Google Scholar logo with link to Google Scholar
De Saussure, Ferdinand, Charles Bally, Albert Sechehaye, Albert Reidlinger, and Wade Baskin
1960 “Course in General Linguistics.” The Journal of American Folklore 73 (289): 274. Google Scholar logo with link to Google Scholar
Deng, Hancheng, and Deyi Xiong
2022 “A Survey on Machine Translation Quality Estimation.” Journal of Chinese Information Processing 36 (11): 20–37.Google Scholar logo with link to Google Scholar
Devlin, Jacob, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova
2019 “BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding.” arXiv, May 24, 2019. https://​arxiv​.org​/abs​/1810​.04805
Dragsted, Barbara
2005 “Segmentation in Translation: Differences Across Levels of Expertise and Difficulty.” Target 17 (1): 49–70. Google Scholar logo with link to Google Scholar
Estrada, Ernesto
2011 The Structure of Complex Networks: Theory and Applications. New York: Oxford University Press. Google Scholar logo with link to Google Scholar
Fan, Lu, and Yue Jiang
2021 “A Syntactic Dependency Network Approach to the Study of Translational Language.” Digital Scholarship in the Humanities 36 (3): 595–606. Google Scholar logo with link to Google Scholar
2023 “Probability Distribution of Dependency Distance and Dependency Type in Translational Language.” Humanities and Social Sciences Communications 10: 1–10. Google Scholar logo with link to Google Scholar
Frankenberg-García, Ana
2021 “Can a Corpus-Driven Lexical Analysis of Human and Machine Translation Unveil Discourse Features That Set Them Apart?” Target 34 (2): 278–308. Google Scholar logo with link to Google Scholar
Freeborn, Lani, Sible Andringa, Gabriela Lunansky, and Judith Rispens
2023 “Network Analysis for Modeling Complex Systems in SLA Research.” Studies in Second Language Acquisition 45 (2): 526–557. Google Scholar logo with link to Google Scholar
Gao, Yuan, Ruili Wang, and Feng Hou
2023 “How to Design Translation Prompts for ChatGPT: An Empirical Study.” arXiv, April 21, 2023. http://​arxiv​.org​/abs​/2304​.02182
Guerberof-Arenas, Ana, and Antonio Toral
2024 “To Be or Not to Be: A Translation Reception Study of a Literary text Translated into Dutch and Catalan Using Machine Translation.” Target 36 (2): 215–244. Google Scholar logo with link to Google Scholar
Halverson, Sandra L.
2010 “Cognitive Translation Studies: Developments in Theory and Method.” In Translation and Cognition, edited by Gregory M. Shreve and Erik Angelone, 349–369. Amsterdam: John Benjamins. Google Scholar logo with link to Google Scholar
Hao, Yuxin, Xuelin Wang, Meng Wu, and Haitao Liu
2021 “Syntactic Networks of Interlanguage Across L2 Modalities and Proficiency Levels.” Frontiers in Psychology 12: 643120. Google Scholar logo with link to Google Scholar
Hendy, Amr, Mohamed Abdelrehim, Amr Sharaf, Vikas Raunak, Mohamed Gabr, Hitokazu Matsushita, Young Jin Kim, Mohamed Afify, and Hany Hassan Awadalla
2023 “How Good are GPT Models at Machine Translation? A Comprehensive Evaluation.” arXiv, June 22, 2023. https://​arxiv​.org​/abs​/2302​.09210
House, Juliane
2014 Translation: A Multidisciplinary Approach. London: Palgrave Macmillan. Google Scholar logo with link to Google Scholar
Hudson, Richard
2007 Language Networks: The New Word Grammar. Oxford: Oxford University Press.Google Scholar logo with link to Google Scholar
Ikram, Muh, Muhammad Nur Akbar Rasyid, and Muh Syukri
2024 “The Evaluation of Machine Translation and Human Translation on YouTube: A Comparative Study.” Journal of Islamic Culture and Literature 3 (1): 101–118.Google Scholar logo with link to Google Scholar
Jiang, Jingyang, Wuzhe Yu, and Haitao Liu
2019 “Does Scale-Free Syntactic Network Emerge in Second Language Learning?” Frontiers in Psychology 10: 925. Google Scholar logo with link to Google Scholar
Jiao, Wenxiang, Wenxuan Wang, Jen tse Huang, Xing Wang, Shuming Shi, and Zhaopeng Tu
2023 “Is ChatGPT a Good Translator? Yes with GPT-4 as the Engine.” arXiv, November 2, 2023. https://​arxiv​.org​/abs​/2301​.08745
Jin, Huiyuan, and Haitao Liu
2016 “Chinese Writing of Deaf or Hard-of-Hearing Students and Normal-Hearing Peers from Complex Network Approach.” Frontiers in Psychology 7: 1777. Google Scholar logo with link to Google Scholar
Jin, Huiyuan, Kecheng Yang, and Haitao Liu
2023 “An Investigation on Ellipsis From Network Science Approach.” Digital Scholarship in the Humanities 38 (3): 1115–1129. Google Scholar logo with link to Google Scholar
Klammer, Thomas P., Muriel Schulz, and Angela Della Volpe
1999 Analyzing English Grammar. New York: Longman.Google Scholar logo with link to Google Scholar
Kolb, Waltraud, Wolfgang U. Dressler, and Elisa Mattiello
2023 “Human and Machine Translation of Occasionalisms in Literary Texts.” Target 35 (4): 540–572. Google Scholar logo with link to Google Scholar
Kübler, Sandra, Ryan McDonald, and Joakim Nivre
2009 Dependency Parsing. Synthesis Lectures on Human Language Technologies. Cham: Springer. Google Scholar logo with link to Google Scholar
Läubli, Samuel, Patrick Simianer, Joern Wuebker, Geza Kovacs, Rico Sennrich, and Spence Green
2021 “The Impact of Text Presentation on Translator Performance.” Target 34 (2): 309–342. Google Scholar logo with link to Google Scholar
Li, Juan, Hongquan Jiang, Aihua Shang, and Jingli Chen
2021 “Research on Associative Learning Mechanisms of L2 Learners Based on Complex Network Theory.” Computer Assisted Language Learning: An International Journal 34 (5–6): 637–662. Google Scholar logo with link to Google Scholar
Li, Yafu, Yongjing Yin, Jing Li, and Yue Zhang
2022 “Prompt-Driven Neural Machine Translation.” In Findings of the Association for Computational Linguistics: ACL 2022, edited by Smaranda Muresan, Preslav Nakov, and Aline Villavicencio, 2579–2590. Dublin: Association for Computational Linguistics. Google Scholar logo with link to Google Scholar
Lin, Yumeng, Duo Xu, and Junying Liang
2021 “Differentiating Interpreting Types: Connecting Complex Networks to Cognitive Complexity.” Frontiers in Psychology 12: 590399. Google Scholar logo with link to Google Scholar
Liu, Haitao, and Chunshan Xu
2011 “Can Syntactic Networks Indicate Morphological Complexity of a Language?” Europhysics Letters 93 (2): 28005. Google Scholar logo with link to Google Scholar
Liu, Haitao
2008 “The Complexity of Chinese Syntactic Dependency Networks.” Physica A: Statistical Machines and its Applications 387 (12): 3048–3058. Google Scholar logo with link to Google Scholar
Liu, Jianpeng, Xinzhuo Shen, Haitao Liu, and Huifang Du
2023 “Dependency Network Approach to the Oral Production of English- and Chinese-speaking Healthy Older Adults.” Speech, Language and Hearing 27 (2): 130–147. Google Scholar logo with link to Google Scholar
Liu, Yiguang, and Junying Liang
2024 “Multidimensional Comparison of Chinese–English Interpreting Outputs From Human and Machine: Implications for Interpreting Education in the Machine-translation Age.” Linguistics and Education 80: 1–13. Google Scholar logo with link to Google Scholar
Luo, Jiaming, Colin Cherry, and George Foster
2024 “To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation.” Transactions of the Association for Computational Linguistics 12: 355–371. Google Scholar logo with link to Google Scholar
Luo, Jinru, and Dechao Li
2022 “Universals in Machine Translation?” International Journal of Corpus Linguistics 27 (1): 31–58. Google Scholar logo with link to Google Scholar
Marshall, Catherine
2024 A Comparative Analysis of Human and Machine Translation Quality. MA thesis. Brigham Young University. https://​scholarsarchive​.byu​.edu​/etd​/10526
Mel’čuk, Igor’ Aleksandrovic
1988 Dependency Syntax: Theory and Practice. Albany: New York Press.Google Scholar logo with link to Google Scholar
Moneus, Ahmed Mohammed, and Yousef Sahari
2024 “Artificial Intelligence and Human Translation: A Contrastive Study Based on Legal Texts.” Heliyon 10 (6): e28106. Google Scholar logo with link to Google Scholar
Mrvar, Andrej, and Vladimir Batagelj
2016 “Analysis and Visualization of Large Networks with Program Package Pajek.” Complex Adaptive Systems Modeling 4: 6. Google Scholar logo with link to Google Scholar
Newman, Mark
2010 Networks: An Introduction. New York: Oxford University Press. Google Scholar logo with link to Google Scholar
Niu, Jiang, Yue Jiang, and Yadong Zhou
2020 “Approaching Textual Coherence of Machine Translation With Complex Network.” International Journal of Modern Physics C 31(12): 2050175. Google Scholar logo with link to Google Scholar
Nivre, Joakim
2006 Inductive Dependency Parsing. Berlin: Springer. Google Scholar logo with link to Google Scholar
Peng, Keqin, Liang Ding, Qihuang Zhong, Li Shen, Xuebo Liu, Min Zhang, Yuanxin Ouyang, and Dacheng Tao
2023 “Towards Making the Most of ChatGPT for Machine Translation.” In Findings of the Association for Computational Linguistics: EMNLP 2023, edited by Houda Bouamor, Juan Pino, and Kalika Bali, 5622–5633. Singapore: Association for Computational Linguistics. Google Scholar logo with link to Google Scholar
Pym, Anthony
2014 Exploring Translation Theories. 2nd ed. Abingdon: Routledge.Google Scholar logo with link to Google Scholar
Radford, Alec, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever
2018 Improving Language Understanding by Generative Pre-Training. Technical report. OpenAI. https://​cdn​.openai​.com​/research​-covers​/language​-unsupervised​/language​_understanding​_paper​.pdf
Solé, Ricard V., Bernat Corominas-Murtra, Sergi Valverde, and Luc Steels
2010 “Language Networks: Their Structure, Function, and Evolution.” Complexity 15 (6): 20–26. Google Scholar logo with link to Google Scholar
Tesnière, Lucien
1959 Éléments De Syntaxe Structurale [Elements of structural syntax]. Paris: Klincksieck.Google Scholar logo with link to Google Scholar
Toury, Gideon
2012 Descriptive Translation Studies — and Beyond. Rev. ed. Amsterdam: John Benjamins. Google Scholar logo with link to Google Scholar
Vaswani, Ashish, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin
2017 “Attention Is All You Need.” In Advances in Neural Information Processing Systems 30, edited by Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett, 6000–6010. Red Hook, NY: Curran Associates.Google Scholar logo with link to Google Scholar
Venuti, Lawrence
1995 The Translator’s Invisibility: A History of Translation. London: Routledge.Google Scholar logo with link to Google Scholar
Wang, Longyue, Chenyang Lyu, Tianbo Ji, Zhirui Zhang, Dian Yu, Shuming Shi, and Zhaopeng Tu
2023 “Document-Level Machine Translation With Large Language Models.” In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, edited by Houda Bouamor, Juan Pino, and Kalika Bali, 16646–16661. Singapore: Association for Computational Linguistics. Google Scholar logo with link to Google Scholar
Watts, Duncan J., and Steven H. Strogatz
1998 “Collective Dynamics of ‘Small-world’ Networks.” Nature 393 (6684): 440–442. Google Scholar logo with link to Google Scholar
White, Jules, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas C. Schmidt
2023 “A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT.” arXiv, July 4, 2024. https://​arxiv​.org​/abs​/2302​.11382
Wu, Minghao, Thuy-Trang Vu, Lizhen Qu, George Foster, and Gholamreza Haffari
2024 “Adapting Large Language Models for Document-Level Machine Translation.” arXiv, November 11, 2024. Google Scholar logo with link to Google Scholar
Yan, Jianhao, Pingchuan Yan, Yulong Chen, Judy Li, Xianchao Zhu, and Yue Zhang
2024 “GPT-4 vs. Human Translators: A Comprehensive Evaluation of Translation Quality Across Languages, Domains, and Expertise Levels.” arXiv, July 4, 2024. https://​arxiv​.org​/abs​/2407​.03658v1
Yu, Shuiyuan, Jin Cong, Junying Liang, and Haitao Liu
2016 “The Distribution of Information Content in English Sentences.” Dblp Computer Science Bibliography. Accessed February 3, 2025. https://​dblp​.org​/rec​/journals​/corr​/YuCLL16​.html
Zhou, Fan
2024 “The Comparison of Translationese in Machine Translation and Human Translation in Terms of Translation Relations.” arXiv, March 27, 2024. https://​arxiv​.org​/abs​/2404​.08661v1
 
Mobile Menu Logo with link to supplementary files background Layer 1 prag Twitter_Logo_Blue