Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sutanto, Vincent Michael, De Giacomo, Giovanni Gatti, Nakazawa, Toshiaki, Yamada, Masaru
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.08042
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
Table des matières:
  • This study investigates ChatGPT for Japanese-English translation, exploring simple and enhanced prompts and comparing against commercially available translation engines. Performing both automatic and MQM-based human evaluations, we found that document-level translation outperforms sentence-level translation for ChatGPT. On the other hand, we were not able to determine if enhanced prompts performed better than simple prompts in our experiments. We also discovered that ChatGPT-3.5 was preferred by automatic evaluation, but a tradeoff exists between accuracy (ChatGPT-3.5) and fluency (ChatGPT-4). Lastly, ChatGPT yields competitive results against two widely-known translation systems.