Optimising ChatGPT for creativity in literary translation: A case study from English into Dutch, Chinese, Catalan and Spanish

• URL: http://arxiv.org/abs/2504.18221v1
• Date: Fri, 25 Apr 2025 10:11:15 GMT
• Title: Optimising ChatGPT for creativity in literary translation: A case study from English into Dutch, Chinese, Catalan and Spanish
• Authors: Shuxiang Du, Ana Guerberof Arenas, Antonio Toral, Kyo Gerrits, Josep Marco Borillo,
• Abstract summary: We evaluate GPT translations in different text levels, temperature settings and prompting strategies with a Creativity Score formula.<n>We found that prompting ChatGPT with a minimal instruction yields the best creative translations.
• Score: 4.527211916001345
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This study examines the variability of Chat-GPT machine translation (MT) outputs across six different configurations in four languages,with a focus on creativity in a literary text. We evaluate GPT translations in different text granularity levels, temperature settings and prompting strategies with a Creativity Score formula. We found that prompting ChatGPT with a minimal instruction yields the best creative translations, with "Translate the following text into [TG] creatively" at the temperature of 1.0 outperforming other configurations and DeepL in Spanish, Dutch, and Chinese. Nonetheless, ChatGPT consistently underperforms compared to human translation (HT).

Related papers

• What is the Best Way for ChatGPT to Translate Poetry? [38.47691441569612]
  This study examines ChatGPT's capabilities in English-Chinese poetry translation tasks, utilizing targeted prompts and small sample scenarios to ascertain optimal performance. We propose an Explanation-Assisted Poetry Machine Translation (EAPMT) method, which leverages monolingual poetry explanation as a guiding information for the translation process. The results from both human and machine evaluations demonstrate that our EAPMT method outperforms traditional translation methods of ChatGPT and the existing online systems.
  arXiv  Detail & Related papers  (2024-06-05T16:48:26Z)
• Exploring the effectiveness of ChatGPT-based feedback compared with teacher feedback and self-feedback: Evidence from Chinese to English translation [1.25097469793837]
  ChatGPT, a cutting-edge AI-powered,can quickly generate responses on given commands. This study compared the revised Chinese to English translation texts produced by Chinese Master of Translation and Interpretation (MTI) students.
  arXiv  Detail & Related papers  (2023-09-04T14:54:39Z)
• Is ChatGPT Involved in Texts? Measure the Polish Ratio to Detect ChatGPT-Generated Text [48.36706154871577]
  We introduce a novel dataset termed HPPT (ChatGPT-polished academic abstracts) It diverges from extant corpora by comprising pairs of human-written and ChatGPT-polished abstracts instead of purely ChatGPT-generated texts. We also propose the "Polish Ratio" method, an innovative measure of the degree of modification made by ChatGPT compared to the original human-written text.
  arXiv  Detail & Related papers  (2023-07-21T06:38:37Z)
• ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning [70.57126720079971]
  Large language models (LLMs) have emerged as the most important breakthroughs in natural language processing (NLP) This paper evaluates ChatGPT on 7 different tasks, covering 37 diverse languages with high, medium, low, and extremely low resources. Compared to the performance of previous models, our extensive experimental results demonstrate a worse performance of ChatGPT for different NLP tasks and languages.
  arXiv  Detail & Related papers  (2023-04-12T05:08:52Z)
• How to Design Translation Prompts for ChatGPT: An Empirical Study [18.678893287863033]
  ChatGPT has demonstrated surprising abilities in natural language understanding and natural language generation. We adopt several translation prompts on a wide range of translations. Our work provides empirical evidence that ChatGPT still has great potential in translations.
  arXiv  Detail & Related papers  (2023-04-05T01:17:59Z)
• Towards Making the Most of ChatGPT for Machine Translation [75.576405098545]
  ChatGPT shows remarkable capabilities for machine translation (MT) Several prior studies have shown that it achieves comparable results to commercial systems for high-resource languages.
  arXiv  Detail & Related papers  (2023-03-24T03:35:21Z)
• A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity [79.12003701981092]
  We carry out an extensive technical evaluation of ChatGPT using 23 data sets covering 8 different common NLP application tasks. We evaluate the multitask, multilingual and multi-modal aspects of ChatGPT based on these data sets and a newly designed multimodal dataset. ChatGPT is 63.41% accurate on average in 10 different reasoning categories under logical reasoning, non-textual reasoning, and commonsense reasoning.
  arXiv  Detail & Related papers  (2023-02-08T12:35:34Z)
• Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine [97.8609714773255]
  We evaluate ChatGPT for machine translation, including translation prompt, multilingual translation, and translation robustness. ChatGPT performs competitively with commercial translation products but lags behind significantly on low-resource or distant languages. With the launch of the GPT-4 engine, the translation performance of ChatGPT is significantly boosted.
  arXiv  Detail & Related papers  (2023-01-20T08:51:36Z)
• mT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs [51.67970832510462]
  We improve multilingual text-to-text transfer Transformer with translation pairs (mT6) We explore three cross-lingual text-to-text pre-training tasks, namely, machine translation, translation pair span corruption, and translation span corruption. Experimental results show that the proposed mT6 improves cross-lingual transferability over mT5.
  arXiv  Detail & Related papers  (2021-04-18T03:24:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.