The impact of postediting on AI generative translation in Yemeni context: Translating literary prose by ChatGPT
Nasim Al-wagieh (Ibb University), Mohammed Q. Shormani (Ibb University)

TL;DR
This study evaluates ChatGPT-4's role in literary translation, highlighting AI's speed benefits and the ongoing need for human postediting to address cultural and stylistic nuances.
Contribution
It provides empirical evidence on AI's limitations in literary translation and advocates for a collaborative human-AI approach rather than full automation.
Findings
AI improves translation speed and accessibility.
Human postediting is essential for cultural and stylistic accuracy.
AI's limitations are prominent in handling figurative language.
Abstract
This study examines the role of artificial intelligence in translation, focusing on ChatGPT, specifically ChatGPT-4, and the extent to which human postediting is required in literary translation. A mixed-method approach was adopted, involving 30 professional translators who evaluated and postedited AI-generated translations of selected Arabic and English literary texts. The results show that although AI improves translation speed and accessibility, it remains limited in handling cultural, stylistic, and figurative aspects of language. Participants generally confirmed the necessity of human postediting, particularly in novels and drama. The findings indicate that emerging human-machine collaboration model rather than replacement of human translators. The study concludes that AI should be used as a supportive tool, while human expertise remains essential for ensuring translation quality…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
