The Journal of Specialised Translation Issue 41 – January 2024

https://doi.org/10.26034/cm.jostrans.2024.4723

© The Authors

Towards Predicting Post-editing Effort with Source Text Readability: An Investigation for English-Chinese Machine Translation

Guangrong Dai, Guangdong University of Foreign Studies

Siqi Liu, Guangdong University of Foreign Studies

这里分享的论文，出自 The Journal of Specialised Translation, 2024年(总第41期)

官网对该期刊的介绍如下：

This international journal is indexed with the main abstract and citation databases of peer-reviewed literature, including the SCOPUS, Clarivate (JCR/Web of Science - AHCI, SSCI), DOAJ, MLA International Bibliography (listed in the Directory of Periodicals), Translation Studies Bibliography, BITRA and ERIH PLUS. JoSTrans is also a member of the Council of Editors of Translation and Interpreting Studies for Open Science.

https://www.jostrans.org/ 

该期刊可以直接登录官网阅读，这里就不全文复制过来了，感兴趣的可以直接下载pdf文档。

ABSTRACT

This paper investigates the impact of source text readability on the effort of post-editing English-Chinese Neural Machine Translation (NMT) output. Six readability formulas, including both traditional and newer ones, were employed to measure readability, and their predictive power towards post-editing effort was evaluated. Keystroke logging, self-report questionnaires, and retrospective protocols were applied to collect the data of post-editing for general text type from thirty-four student translators. The results reveal that: 1) readability has a significant yet weak effect on cognitive effort, while its impact on temporal and technical effort is less pronounced; 2) high NMT quality may alleviate the effect of readability; 3) readability formulas have the ability to predict post-editing effort to a certain extent, and newer formulas such as the Crowdsourced Algorithm of Reading Comprehension (CAREC) outperformed traditional formulas in most cases. Apart from readability formulas, the study shows that some fine-grained reading-related linguistic features are good predictors of post-editing time. Finally, this paper provides implications for automatic effort estimation in the translation industry.

KEYWORDS

Neural machine translation, post-editing effort, readability, key logging, student translator.

Acknowledgements 

This research was supported by the National Social Science Fund of China (“神经网络机器翻译质量提升研究”/“A Study on Quality Improvement of Neural Machine Translation”, Grant reference: 22BYY042). The authors would like to thank our participants and evaluators for their valuable time. Heartfelt gratitude is extended to the editors, the anonymous reviewers, and Dr. Jiajun Qian for their constructive comments and insightful feedback.

Biography

Guangrong DAI (Ph.D) is a Professor at the School of Interpreting and Translation Studies, Guangdong University of Foreign Studies, China. His main research interests cover corpus translation studies, NLP and MTPE. He is also interested in new technologies and their affordances as well as pedagogical theories that facilitate the teaching of those technologies. His blog is http://blog.sciencenet.cn/u/carldy.

ORCID: 0000-0001-7785-8484

E-mail: carldy@163.com

Siqi Liu is an MA student at the School of Interpreting & Translation Studies, Guangdong University of Foreign Studies, China. Her research interests include translation/post-editing process research and corpus-assisted translation teaching. She is also passionate about doing translation education research from interdisciplinary perspectives, for instance, using psychology.

ORCID: 0000-0002-1856-3376

E-mail: 20211210023@gdufs.edu.cn 

https://doi.org/10.26034/cm.jostrans.2024.4723

文献格式：

Dai, G., & Liu, S. (2024). Towards Predicting Post-editing Effort with Source Text Readability: 

An Investigation for English-Chinese Machine Translation. 

The Journal of Specialised Translation(41), 206-229. 

doi:10.26034/cm.jostrans.2024.4723 

附上论文全文pdf：

8.+Dai+and+Liu.pdf