Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text

Rui Sun

doi:doi:10.11648/j.ijalt.20261204.11

Research Article |

| Peer-Reviewed

Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text

Rui Sun^*

Published in International Journal of Applied Linguistics and Translation (Volume 12, Issue 4)

Received: 29 September 2026 Accepted: 14 October 2026 Published: 28 October 2026

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

With the rapid development of generative AI, increasing attention has been paid to its potential in translation practice. This study aims to investigate generative AI’s use of explicitation in translation. It compares the official English translation of an international publicity text on China’s green and low-carbon industrial transition, released by the State Council Information Office, with translations generated by ChatGPT and DeepSeek. Drawing on focus-point analysis, the study first identifies focus points through a comparison between the Chinese source text and its official English translation to examine explicitation use, and subsequently examines how the two generative AI models address these points. The findings reveal that ChatGPT and DeepSeek demonstrate a tendency towards explicitation, with their outputs showing considerable similarity to the official translation. Both models are effective in making implicit linguistic relations explicit, including omitted subjects, possessive relations, and logical connections between linguistic elements. However, generative AI’s explicitation is primarily concentrated at the linguistic level. Compared with the official translation, the two models show limitations in preserving the stylistic features of the international publicity text and providing culture-specific background information. These findings suggest that while generative AI may serve as an effective tool for initial translation drafting, human involvement remains important for stylistic refinement and culturally informed decision-making. The study contributes to a better understanding of the capabilities and limitations of generative AI in Chinese-English translation and offers implications for the broader use of generative AI in international communication.

Published in	International Journal of Applied Linguistics and Translation (Volume 12, Issue 4)
DOI	10.11648/j.ijalt.20261204.11
Page(s)	68-78
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2026. Published by Science Publishing Group

Keywords

Explicitation, Generative AI Translation, Chinese-English Translation, Policy Translation, ChatGPT, DeepSeek

References

[1]	Vinay, J.-P., Darbelnet, J. Comparative Stylistics of French and English: A Methodology for Translation; Translated by Sager, J. C. from Stylistique comparée du français et de l'anglais: Méthode de traduction published in 1958, Amsterdam: John Benjamins Publishing Company; 1995, p. 342.
[2]	Blum-Kulka, S. Shifts of Cohesion and Coherence in Translation. In Interlingual and Intercultural Communication: Discourse and Cognition in Translation and Second Language Acquisition Studies, Blum-Kulka, S., House, J., Eds., Tübingen: Gunter Narr Verlag; 1986, pp. 17-36.
[3]	Séguinot, C. Pragmatics and the Explicitation Hypothesis. TTR . 1988, 1(2), 106-113. https://doi.org/10.7202/037024ar
[4]	Baker, M. Corpus-Based Translation Studies: The Challenges That Lie Ahead. In Terminology, LSP and Translation: Studies in Language Engineering in Honour of Juan C. Sager, Somers, H., Ed., Amsterdam: John Benjamins Publishing Company; 1996, pp. 175-186.
[5]	Alasmri, I., Kruger, H. Conjunctive Markers in Translation from English to Arabic: A Corpus-Based Study. Perspectives. 2018, 26(5), 767-788. https://doi.org/10.1080/0907676X.2018.1425463
[6]	Chen, J. W. Explicitation through the Use of Connectives in Translated Chinese: A Corpus-Based Study. Ph.D. Thesis, University of Manchester, 2006.
[7]	Marco, J. Connectives as Indicators of Explicitation in Literary Translation: A Study Based on a Comparable and Parallel Corpus. Target. 2018, 30(1), 87-111. https://doi.org/10.1075/target.16042.mar
[8]	Zhang, X., Kotze, H., Fang, J. Explicitation in Children’s Literature Translated from English to Chinese: A Corpus-Based Study of Personal Pronouns. Perspectives. 2020, 28(5), 717-736. https://doi.org/10.1080/0907676X.2019.1689276
[9]	Rojo, L. A., Valenzuela, J. How to Say Things with Words: Ways of Saying in English and Spanish. Meta. 2001, 46(3), 467-477. https://doi.org/10.7202/003971ar
[10]	Baker, M. Corpus Linguistics and Translation Studies: Implications and Applications. In Text and Technology: In Honour of John Sinclair, Francis, G., Tognini-Bonelli, E. Eds., Amsterdam: John Benjamins Publishing Company; 1993, pp. 233-250.
[11]	Saldanha, G. Style of Translation: The Use of Foreign Words in Translations by Margaret Jull Costa and Peter Bush. In Corpus-Based Translation Studies: Research and Applications, Wallmach, K., Kruger, A., Munday, J. Eds., London: Bloomsbury; 2011, pp. 237-259.
[12]	Klaudy, K. Explicitation. In Routledge Encyclopedia of Translation Studies, Baker, M., Saldanha, G. Eds., London: Routledge; 2008, pp. 104-108.
[13]	Øverås, L. In Search of the Third Code: An Investigation of Norms in Literary Translation. Meta. 1998, 43(4), 557-570. https://doi.org/10.7202/003775ar
[14]	Olohan, M., Baker, M. Reporting That in Translated English. Evidence For Subconscious Process of Explicitation? Across Languages and Cultures. 2000, 1(2), 141-158. https://doi.org/10.1556/Acr.1.2000.2.1
[15]	Klaudy, K., Károly, K. Implicitation in Translation: Empirical Evidence for Operational Asymmetry in Translation. Across Languages and Cultures. 2005, 6(1), 13-28. https://doi.org/10.1556/Acr.6.2005.1.2
[16]	Jiménez-Crespo, M. A. The Future of General Tendencies in Translation: Explicitation in Web Localization. Target. 2011, 23(1), 3-25. https://doi.org/10.1075/target.23.1.01jim
[17]	Beikian, A., Yarahmadzehi, N., Natanzi, M. K. Explicitation of Conjunctive Relations in Ghabraei’s Persian Translation of The Kite Runner. English Language and Literature Studies. 2013, 3(2), 81-89. https://doi.org/10.5539/ells.v3n2p81
[18]	Feng, H., Crezee, I., Grant, L. Form and Meaning in Collocations: A Corpus-Driven Study on Translation Universals in Chinese-to-English Business Translation. Perspectives. 2018, 26(5), 677-690. https://doi.org/10.1080/0907676X.2018.1424222
[19]	Papineni, K., Roukos, S., Ward, T., Zhu, W.-J. BLEU: A Method for Automatic Evaluation of Machine Translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadephia, USA, 2002; pp. 311-318. https://doi.org/10.3115/1073083.1073135
[20]	Snover, M., Dorr, B., Schwartz, R., Micciulla, L., Makhoul, J. A Study of Translation Edit Rate with Targeted Human Annotation. In Proceedings of the 7th Conference of the Association for Machine Translation in the Americas: Technical Papers, Massachusetts, USA, 2006; pp. 223-231.
[21]	Popović, M. ChrF: Character N-gram F-score for Automatic MT Evaluation. In Proceedings of the Tenth Workshop on Statistical Machine Translation, Lisbon, Portugal, 2015; pp. 392-395. https://doi.org/10.18653/v1/W15-3049
[22]	Popović, M. ChrF++: Words Helping Character N-grams. In Proceedings of the Second Conference on Machine Translation, Copenhagen, Denmark, 2017, pp. 612-618. https://doi.org/10.18653/v1/W17-4770
[23]	Son, J., Kim, B. Translation Performance from the User’s Perspective of Large Language Models and Neural Machine Translation Systems. Information. 2023, 14, 574. https://doi.org/10.3390/info14100574
[24]	Jiao, W., Wang, W., Huang, J., Wang, X., Shi, S., Tu, J. Is ChatGPT a Good Translator? Yes with GPT-4 as The Engine. arXiv. 2023. https://doi.org/10.48550/arXiv.2301.08745
[25]	Hendy, A., Abdelrehim, M., Sharaf, A., Raunak, V., Gabr, M., Matsushita, H., Kim, Y. J., Afify, M., Awadalla, H. H. How Good Are GPT Models at Machine Translation? A Comprehensive Evaluation. arXiv. https://doi.org/10.48550/arXiv.2302.09210
[26]	Alkhawaja, L. Unveiling the New Frontier: ChatGPT-3 Powered Translation for Arabic-English Language Pairs. Theory and Practice in Language Studies. 2024, 14(2), 347-357. https://doi.org/10.17507/tpls.1402.05
[27]	Cetin, E. D., Sahin, C. Multi-Metric Evaluation of Translation-Based Cross-Lingual Sentiment Consistency Using Large Language Models and Neural Machine Translation. Applied Sciences. 2026, 16(16), 7878. https://doi.org/10.3390/app16167878
[28]	Wang, Q., Wang, Y., Amini, M., Xian, M., Fu, Z. Quality Assessment of Tibetan-Chinese Poetry Translation: Integrating Automated Metrics and Qualitative Insights Through a Cross-System Comparison of Dedicated NMT Engines and a Prompted LLM. Language Resources and Evaluation. 2026, 60. https://doi.org/10.1007/s10579-026-09918-8
[29]	Zayed, A. B. Evaluating the Fidelity and Accuracy of ChatGPT 4 and Google Translate in Translating Legal English Documents into Arabic—and Vice Versa. Journal of the Faculty of Languages, University of Tripoli, Libya. 2024, 1(29), 64-87.
[30]	Sun, R. Evaluating the Translation Accuracy of ChatGPT and DeepL Through the Lens of Implied Subjects. AWEJ for Translation & Literary Studies. 2024, 8(4), 41-53. https://doi.org/10.24093/awejtls/vol8no4.5
[31]	AlAfnan, M. A. Large Language Models as Computational Linguistics Tools: A Comparative Analysis of ChatGPT and Google Machine Translations. Journal of Artificial Intelligence and Technology. 2024, 5, 20-32. https://doi.org/10.37965/jait.2024.0549
[32]	Dong, L. A Comparative Study on the Translation Quality of Chinese Diplomatic Discourse by NMT and LLMs Based on Multidimensional Quality Metrics. International Journal of Applied Linguistics and Translation. 2025, 11(4), 107-115. https://doi.org/10.11648/j.ijalt.20251104.12
[33]	Castilho, S., Mallon, C. Q., Meister, R., Yue, S. Do Online Machine Translation Systems Care for Context? What About a GPT Model? In Proceedings of the 24th Annual Conference of the European Association for Machine Translation, Tampere, Finland, 2023; pp. 393-417.
[34]	Du, Y., Liu, L., Liu, Z. The Limitations of ChatGPT Translation—The Comparative Case Study of ChatGPT Translation and Human Translation. Journal of North China Electric Power University (Social Sciences). 2025 (6), 92-101. https://doi.org/10.14092/j.cnki.cn11-3956/c.2025.12.015
[35]	Zhao, Q., Lin, S. Translator Behavior Criticism in the Context of Human-Machine Translation: A Case Study of that Explicitation in the English Translation of Xi Jinping: The Governance of China. Journal of Tianjin Foreign Studies University. 2026, 33(3), 38-49+112-113.
[36]	Peng, K., Ding, L., Zhong, Q., Shen, L., Liu, X., Zhang, M., Ouyang, Y., Tao, D. Towards Making the Most of ChatGPT for Machine Translation. arXiv. 2023. https://doi.org/10.48550/arXiv.2303.13780
[37]	Yamada, M. Optimizing Machine Translation through Prompt Engineering: An Investigation into ChatGPT’s Customizability. arXiv. 2024. https://doi.org/10.48550/arxiv.2308.01391
[38]	Aldosari, L. A., Altuwairesh, N. Assessing the Effects of Translation Prompts on the Translation Quality of GPT-4 Turbo Using Automated and Human Evaluation Metrics: A Case Study. Perspectives (published online first on 08 May 2025). 1-25. https://doi.org/10.1080/0907676X.2025.2464120
[39]	Hjort-Pedersen, M., Faber, D. Explicitation and Implicitation in Legal Translation—A Process Study of Trainee Translators. Meta. 2010, 55(2), 237-250. https://doi.org/10.7202/044237ar

Cite This Article

Plain Text BibTeX RIS

APA Style

Sun, R. (2026). Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text. International Journal of Applied Linguistics and Translation, 12(4), 68-78. https://doi.org/10.11648/j.ijalt.20261204.11

Copy | Download

ACS Style

Sun, R. Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text. Int. J. Appl. Linguist. Transl. 2026, 12(4), 68-78. doi: 10.11648/j.ijalt.20261204.11

Copy | Download

AMA Style

Sun R. Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text. Int J Appl Linguist Transl. 2026;12(4):68-78. doi: 10.11648/j.ijalt.20261204.11

Copy | Download

@article{10.11648/j.ijalt.20261204.11,
  author = {Rui Sun},
  title = {Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text},
  journal = {International Journal of Applied Linguistics and Translation},
  volume = {12},
  number = {4},
  pages = {68-78},
  doi = {10.11648/j.ijalt.20261204.11},
  url = {https://doi.org/10.11648/j.ijalt.20261204.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijalt.20261204.11},
  abstract = {With the rapid development of generative AI, increasing attention has been paid to its potential in translation practice. This study aims to investigate generative AI’s use of explicitation in translation. It compares the official English translation of an international publicity text on China’s green and low-carbon industrial transition, released by the State Council Information Office, with translations generated by ChatGPT and DeepSeek. Drawing on focus-point analysis, the study first identifies focus points through a comparison between the Chinese source text and its official English translation to examine explicitation use, and subsequently examines how the two generative AI models address these points. The findings reveal that ChatGPT and DeepSeek demonstrate a tendency towards explicitation, with their outputs showing considerable similarity to the official translation. Both models are effective in making implicit linguistic relations explicit, including omitted subjects, possessive relations, and logical connections between linguistic elements. However, generative AI’s explicitation is primarily concentrated at the linguistic level. Compared with the official translation, the two models show limitations in preserving the stylistic features of the international publicity text and providing culture-specific background information. These findings suggest that while generative AI may serve as an effective tool for initial translation drafting, human involvement remains important for stylistic refinement and culturally informed decision-making. The study contributes to a better understanding of the capabilities and limitations of generative AI in Chinese-English translation and offers implications for the broader use of generative AI in international communication.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text
AU  - Rui Sun
Y1  - 2026/10/28
PY  - 2026
N1  - https://doi.org/10.11648/j.ijalt.20261204.11
DO  - 10.11648/j.ijalt.20261204.11
T2  - International Journal of Applied Linguistics and Translation
JF  - International Journal of Applied Linguistics and Translation
JO  - International Journal of Applied Linguistics and Translation
SP  - 68
EP  - 78
PB  - Science Publishing Group
SN  - 2472-1271
UR  - https://doi.org/10.11648/j.ijalt.20261204.11
AB  - With the rapid development of generative AI, increasing attention has been paid to its potential in translation practice. This study aims to investigate generative AI’s use of explicitation in translation. It compares the official English translation of an international publicity text on China’s green and low-carbon industrial transition, released by the State Council Information Office, with translations generated by ChatGPT and DeepSeek. Drawing on focus-point analysis, the study first identifies focus points through a comparison between the Chinese source text and its official English translation to examine explicitation use, and subsequently examines how the two generative AI models address these points. The findings reveal that ChatGPT and DeepSeek demonstrate a tendency towards explicitation, with their outputs showing considerable similarity to the official translation. Both models are effective in making implicit linguistic relations explicit, including omitted subjects, possessive relations, and logical connections between linguistic elements. However, generative AI’s explicitation is primarily concentrated at the linguistic level. Compared with the official translation, the two models show limitations in preserving the stylistic features of the international publicity text and providing culture-specific background information. These findings suggest that while generative AI may serve as an effective tool for initial translation drafting, human involvement remains important for stylistic refinement and culturally informed decision-making. The study contributes to a better understanding of the capabilities and limitations of generative AI in Chinese-English translation and offers implications for the broader use of generative AI in international communication.
VL  - 12
IS  - 4
ER  -

Copy | Download

Author Information

Rui Sun

School of Foreign Studies, University of Science and Technology Beijing, Beijing, China

Contact Email

http://orcid.org/0000-0003-3552-9601

Download PDF

Submit an Article

Sections

Plain Text BibTeX RIS

APA Style

Sun, R. (2026). Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text. International Journal of Applied Linguistics and Translation, 12(4), 68-78. https://doi.org/10.11648/j.ijalt.20261204.11

Copy | Download

ACS Style

Sun, R. Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text. Int. J. Appl. Linguist. Transl. 2026, 12(4), 68-78. doi: 10.11648/j.ijalt.20261204.11

Copy | Download

AMA Style

Sun R. Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text. Int J Appl Linguist Transl. 2026;12(4):68-78. doi: 10.11648/j.ijalt.20261204.11

Copy | Download

@article{10.11648/j.ijalt.20261204.11,
  author = {Rui Sun},
  title = {Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text},
  journal = {International Journal of Applied Linguistics and Translation},
  volume = {12},
  number = {4},
  pages = {68-78},
  doi = {10.11648/j.ijalt.20261204.11},
  url = {https://doi.org/10.11648/j.ijalt.20261204.11},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijalt.20261204.11},
  abstract = {With the rapid development of generative AI, increasing attention has been paid to its potential in translation practice. This study aims to investigate generative AI’s use of explicitation in translation. It compares the official English translation of an international publicity text on China’s green and low-carbon industrial transition, released by the State Council Information Office, with translations generated by ChatGPT and DeepSeek. Drawing on focus-point analysis, the study first identifies focus points through a comparison between the Chinese source text and its official English translation to examine explicitation use, and subsequently examines how the two generative AI models address these points. The findings reveal that ChatGPT and DeepSeek demonstrate a tendency towards explicitation, with their outputs showing considerable similarity to the official translation. Both models are effective in making implicit linguistic relations explicit, including omitted subjects, possessive relations, and logical connections between linguistic elements. However, generative AI’s explicitation is primarily concentrated at the linguistic level. Compared with the official translation, the two models show limitations in preserving the stylistic features of the international publicity text and providing culture-specific background information. These findings suggest that while generative AI may serve as an effective tool for initial translation drafting, human involvement remains important for stylistic refinement and culturally informed decision-making. The study contributes to a better understanding of the capabilities and limitations of generative AI in Chinese-English translation and offers implications for the broader use of generative AI in international communication.},
 year = {2026}
}

Copy | Download

TY  - JOUR
T1  - Explicitation in Generative AI Translation: A Comparative Analysis of ChatGPT and DeepSeek in Translating a Chinese Policy Text
AU  - Rui Sun
Y1  - 2026/10/28
PY  - 2026
N1  - https://doi.org/10.11648/j.ijalt.20261204.11
DO  - 10.11648/j.ijalt.20261204.11
T2  - International Journal of Applied Linguistics and Translation
JF  - International Journal of Applied Linguistics and Translation
JO  - International Journal of Applied Linguistics and Translation
SP  - 68
EP  - 78
PB  - Science Publishing Group
SN  - 2472-1271
UR  - https://doi.org/10.11648/j.ijalt.20261204.11
AB  - With the rapid development of generative AI, increasing attention has been paid to its potential in translation practice. This study aims to investigate generative AI’s use of explicitation in translation. It compares the official English translation of an international publicity text on China’s green and low-carbon industrial transition, released by the State Council Information Office, with translations generated by ChatGPT and DeepSeek. Drawing on focus-point analysis, the study first identifies focus points through a comparison between the Chinese source text and its official English translation to examine explicitation use, and subsequently examines how the two generative AI models address these points. The findings reveal that ChatGPT and DeepSeek demonstrate a tendency towards explicitation, with their outputs showing considerable similarity to the official translation. Both models are effective in making implicit linguistic relations explicit, including omitted subjects, possessive relations, and logical connections between linguistic elements. However, generative AI’s explicitation is primarily concentrated at the linguistic level. Compared with the official translation, the two models show limitations in preserving the stylistic features of the international publicity text and providing culture-specific background information. These findings suggest that while generative AI may serve as an effective tool for initial translation drafting, human involvement remains important for stylistic refinement and culturally informed decision-making. The study contributes to a better understanding of the capabilities and limitations of generative AI in Chinese-English translation and offers implications for the broader use of generative AI in international communication.
VL  - 12
IS  - 4
ER  -

Copy | Download