GenAI as a translation assistant? A corpus-based study on lexical and syntactic complexity of GPT-post-edited learner translation
Ho Ling Kwok, Yining Shi, Xu Han, Dechao Li, Kanglong Liu
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.