Proceedings of the 2024 2nd International Conference on Language, Innovative Education and Cultural Communication (CLEC 2024)

<Previous Article In Volume
Next Article In Volume>

Thematic Structure and Discourse Coherence in Neural Machine Translation of News Discourse: A Comparative Analysis of GPT-4 Based Translate and Google Translate

Authors
Shan Wang1, *
1School of Foreign Languages and Literature, Beijing Normal University, 100875, Beijing, China
*Corresponding author. Email: Boobi2000@163.com
Corresponding Author
Shan Wang
Available Online 3 July 2024.
DOI
10.2991/978-2-38476-263-7_36How to use a DOI?
Keywords
Machine Translation; Large Language Models; Thematic Structure Theory; Discourse Coherence
Abstract

Employing the thematic structure theory, this study investigates the differences in discourse coherence between large language model-based machine translation and traditional neural machine translation in Chinese-English news discourse translation. Findings reveal that large language model-based machine translation more closely resembles human translation in constructing thematic systems and progression patterns, although it may still exhibit limitations in discourse organization compared to human translators. Traditional neural machine translation, on the other hand, tends to overuse constant theme progression, resulting in a lack of discourse hierarchy. This research provides empirical evidence for the application of thematic structure theory in machine translation evaluation and offers insights into optimizing large language model-based machine translation systems to enhance translation coherence.

Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2024 2nd International Conference on Language, Innovative Education and Cultural Communication (CLEC 2024)
Series
Advances in Social Science, Education and Humanities Research
Publication Date
3 July 2024
ISBN
10.2991/978-2-38476-263-7_36
ISSN
2352-5398
DOI
10.2991/978-2-38476-263-7_36How to use a DOI?
Copyright
© 2024 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Shan Wang
PY  - 2024
DA  - 2024/07/03
TI  - Thematic Structure and Discourse Coherence in Neural Machine Translation of News Discourse: A Comparative Analysis of GPT-4 Based Translate and Google Translate
BT  - Proceedings of the 2024 2nd International Conference on Language, Innovative Education and Cultural Communication (CLEC 2024)
PB  - Atlantis Press
SP  - 282
EP  - 289
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-263-7_36
DO  - 10.2991/978-2-38476-263-7_36
ID  - Wang2024
ER  -