The impact of postediting on AI generative translation in Yemeni context: Translating literary prose by ChatGPT

arXiv cs.CL / 4/21/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The study evaluates ChatGPT-4’s generative translation performance for literary prose in a Yemeni/Arabic-English context, focusing on how much human postediting is still needed.
Using a mixed-method study with 30 professional translators who assessed and postedited AI outputs, the research finds AI increases translation speed and accessibility.
However, AI remains limited in accurately capturing culturally grounded, stylistic, and figurative language features that are crucial for literary translation.
Participants broadly conclude that human postediting is necessary, especially for novels and drama, supporting a human–machine collaboration model rather than replacement of human translators.
The paper recommends using AI as a supportive tool while keeping human expertise central to achieving translation quality and cultural appropriateness.

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 and cultural appropriateness.