AI meets comedy: Viewers' reactions to GPT-4 generated humor translation

Q1 Arts and Humanities
Hussein Abu-Rayyash
{"title":"AI meets comedy: Viewers' reactions to GPT-4 generated humor translation","authors":"Hussein Abu-Rayyash","doi":"10.1016/j.amper.2023.100162","DOIUrl":null,"url":null,"abstract":"<div><p>In the context of the rapidly evolving AI-generated translation landscape, this study explores the viewer experience of GPT-4-generated humor translations compared to human translations for dubbing purposes. Despite advances in AI technology, challenges persist in capturing the nuances of humor and cultural references, which are essential for effective humor translation. A group of cinephiles was provided with humor dialogues translated using both GPT-4-generated and human translations and were then asked to fill out a questionnaire evaluating five constructs: quality, comprehension, enjoyment, perception, and suggestions for improvement. The results indicate that GPT-4-generated translations can offer an equivalent or superior viewer experience to human translations. However, the results also highlight the potential of GPT-4-generated translation in humor translation and emphasize the need to refine AI algorithms, foster collaboration between AI and human translators, and establish quality standards for AI-generated translations based on audience preferences and evolving trends in humor.</p></div>","PeriodicalId":35076,"journal":{"name":"Ampersand","volume":"12 ","pages":"Article 100162"},"PeriodicalIF":0.0000,"publicationDate":"2023-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2215039023000553/pdfft?md5=47b14214e1803bb13cc1cfc443194f33&pid=1-s2.0-S2215039023000553-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ampersand","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2215039023000553","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Arts and Humanities","Score":null,"Total":0}
引用次数: 0

Abstract

In the context of the rapidly evolving AI-generated translation landscape, this study explores the viewer experience of GPT-4-generated humor translations compared to human translations for dubbing purposes. Despite advances in AI technology, challenges persist in capturing the nuances of humor and cultural references, which are essential for effective humor translation. A group of cinephiles was provided with humor dialogues translated using both GPT-4-generated and human translations and were then asked to fill out a questionnaire evaluating five constructs: quality, comprehension, enjoyment, perception, and suggestions for improvement. The results indicate that GPT-4-generated translations can offer an equivalent or superior viewer experience to human translations. However, the results also highlight the potential of GPT-4-generated translation in humor translation and emphasize the need to refine AI algorithms, foster collaboration between AI and human translators, and establish quality standards for AI-generated translations based on audience preferences and evolving trends in humor.

人工智能遇上喜剧:观众对 GPT-4 生成的幽默翻译的反应
在人工智能生成翻译迅速发展的背景下,本研究探讨了 GPT-4 生成的幽默翻译与用于配音的人工翻译相比的观众体验。尽管人工智能技术在不断进步,但在捕捉幽默的细微差别和文化内涵方面仍然存在挑战,而这对于有效翻译幽默至关重要。我们向一组电影爱好者提供了使用 GPT-4 生成的和人工翻译的幽默对话,然后要求他们填写一份调查问卷,对五个方面进行评估:质量、理解、欣赏、感知和改进建议。结果表明,GPT-4 生成的译文可以为观众提供与人工翻译相当或更好的体验。不过,结果也凸显了 GPT-4 生成的译文在幽默翻译中的潜力,并强调有必要完善人工智能算法,促进人工智能与人类译者之间的合作,并根据受众的偏好和幽默的发展趋势为人工智能生成的译文建立质量标准。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Ampersand
Ampersand Arts and Humanities-Language and Linguistics
CiteScore
1.60
自引率
0.00%
发文量
9
审稿时长
24 weeks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信