GenAI as a translation assistant? A corpus-based study on lexical and syntactic complexity of GPT-post-edited learner translation

IF 4.9 1区文学 Q1 EDUCATION & EDUCATIONAL RESEARCH

System Pub Date : 2025-02-10 DOI:10.1016/j.system.2025.103618

Ho Ling Kwok, Yining Shi, Han Xu, Dechao Li, Kanglong Liu

{"title":"GenAI as a translation assistant? A corpus-based study on lexical and syntactic complexity of GPT-post-edited learner translation","authors":"Ho Ling Kwok, Yining Shi, Han Xu, Dechao Li, Kanglong Liu","doi":"10.1016/j.system.2025.103618","DOIUrl":null,"url":null,"abstract":"<div><div>The advent of generative artificial intelligence (GenAI) models, most notably ChatGPT in late 2022, marked a significant milestone in AI development, attracting widespread attention from various research fields. Among its emerging applications, GenAI demonstrates potential in translation education. This study examines the role of GenAI as a post-editing assistant in learner translation by comparing the lexical and syntactic complexity of second language (L2) translations produced by Hong Kong students, with and without post-editing by GPT. The analysis revealed that GPT post-editing improved lexical complexity in learner translations, though its effect on syntactic complexity was inconsistent. While GPT post-editing resulted in longer clauses, more complex nominals, and an increased use of coordinate phrases, non-edited translations featured greater subordination and more verbal structures. These findings suggest that GenAI holds promise in enhancing translation practice but also highlight the need for critical AI literacy to ensure effective use in translation education, particularly in advancing students’ linguistic and instrumental competence.</div></div>","PeriodicalId":48185,"journal":{"name":"System","volume":"130 ","pages":"Article 103618"},"PeriodicalIF":4.9000,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"System","FirstCategoryId":"98","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0346251X25000284","RegionNum":1,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"EDUCATION & EDUCATIONAL RESEARCH","Score":null,"Total":0}

引用次数: 0

Abstract

The advent of generative artificial intelligence (GenAI) models, most notably ChatGPT in late 2022, marked a significant milestone in AI development, attracting widespread attention from various research fields. Among its emerging applications, GenAI demonstrates potential in translation education. This study examines the role of GenAI as a post-editing assistant in learner translation by comparing the lexical and syntactic complexity of second language (L2) translations produced by Hong Kong students, with and without post-editing by GPT. The analysis revealed that GPT post-editing improved lexical complexity in learner translations, though its effect on syntactic complexity was inconsistent. While GPT post-editing resulted in longer clauses, more complex nominals, and an increased use of coordinate phrases, non-edited translations featured greater subordination and more verbal structures. These findings suggest that GenAI holds promise in enhancing translation practice but also highlight the need for critical AI literacy to ensure effective use in translation education, particularly in advancing students’ linguistic and instrumental competence.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

System Multiple-

CiteScore

8.80

自引率

8.30%

发文量

202

审稿时长

64 days

期刊介绍： This international journal is devoted to the applications of educational technology and applied linguistics to problems of foreign language teaching and learning. Attention is paid to all languages and to problems associated with the study and teaching of English as a second or foreign language. The journal serves as a vehicle of expression for colleagues in developing countries. System prefers its contributors to provide articles which have a sound theoretical base with a visible practical application which can be generalized. The review section may take up works of a more theoretical nature to broaden the background.