ChatGPT and MT-Systems: advantages and limitations when translating english to spanish and portuguese

  1. María Labarta Postigo
Revista:
Lengua y Habla

ISSN: 2244-811X

Año de publicación: 2024

Título del ejemplar: Enero-Diciembre

Número: 28

Páginas: 369-390

Tipo: Artículo

DIALNET GOOGLE SCHOLAR lock_openAcceso abierto editor

Otras publicaciones en: Lengua y Habla

Resumen

The translation landscape is changing significantly with the advent of genAI-powered chatbots like ChatGPT. Machine translation (MT) systems have been at the forefront of translation technology since the 1950s, but the new genAI models represent a transformative shift. This study explores the advantages and limitations of translating English to Portuguese and Spanish using Machine Translation (MT) systems and ChatGPT. MT systems have improved significantly over the last years, and large language models (LLMs), democratized recently by ChatGPT, have also recently proved to be effective at translating text. Nevertheless, these systems still face challenges in accurately capturing different languages’ cultural specificities, nuances, and complexities. This paper analyzes translations performed by various chatbots and MT systems, including Systran, Google Translation, DeepL, Chat AI GPT (free), Bing Chatbot (powered by ChatGPT), and Google's Bard. The data analysis is presented from a cognitive and contrastive perspective, following the author's recent methodology. The aim is to evaluate their overall performance and effectiveness. The results reveal that translating from English to Spanish and Portuguese presents significant challenges for all systems and tools, including grammatical and semantical issues. Additionally, notable differences have been observed between the translations performed by the MT-Systems and those from genAI chatbots. Finally, this paper will discuss the advantages and limitations of MT-translation systems and their implications for the role of human translators.

Referencias bibliográficas

  • Alawida,Moatsum,Mejri,Sami,Mehmood,Abid,Chikhaoui,Belkacem & Abiodun,Oludare Isaac.2023.A Comprehensive Study of ChatGPT:Advancements,Limitations,and Ethical Considerations in Natural Language Processing and Cybersecurity,Information 14(8),462,1-23.
  • Baker,Mona.1992.In other words–A Coursebook of Translation.Routledge.
  • Boase-Beier,Jean,2006.Stylistic Approaches to Translation.St Jerome Publishing.
  • Conca,Maria & Guia,Josep.2014.La fraseologia.Principis,mètode i aplicacions.Valencia:Bromera/Institut Interuniversitari de Filologia Valenciana.
  • Corpas,Gloria.2000.Acerca de la (in)traducibilidad de la fraseología.En G.Corpas(ed.),Las lenguas de Europa:Estudios de fraseología,fraseografía y traducción(pp.483-522).Comares.
  • Chomsky,Noam,Roberts,Ian Roberts & Watumull,Jeffrey(2023).Noam Chomsky:The false promise of ChatGPT.New York Times.Díaz Cintas,Jaume & Remael,Aline.2014.Audiovisual Translation:Subtitling.Routledge.
  • Díaz Cintas,Jaume y Remael,Aline.2020.Subtitling.Concepts and Practices.Routledge.
  • Dwyer,Tessa.2017.Speaking in Subtitles:Revaluing Screen Translation.Edinburgh University Press.
  • Gibbs,Raymond W.,Nayak,N.P.& Cutting,C.1989.How to kick the Bucket and Not Decompose:Analyzabitity and Idiom Processing.Journal of Memory and Language 28,576–593.
  • Gibbs,Raymond W.,& O’Brien,Jennifer E.1990.Idioms and mental imagery:The metaphorical motivation for idiomatic meaning. Cognition 36,35–68.Gibbs,Raymond
  • W.,Bogdanovich,J.M.,Sykes,J.R.,& Barr,D.J.1997.Metaphor in Idiom Comprehension.Journal of Memory and Language 37,141–154.Gibbs,Raymond W.2001.Proverbial themes we live by.oetics 29,167-188.
  • Huang,Jin-Xia,Lee,Kyung-Soon,Kim,Young-Kil.2020.Hybrid Translation with Classification:Revisiting,Rule-Based and Neural Machine Translation.Electronics,9(2),201-218.
  • Hellmich,Emily.A.,& Vinall,Kimberly(eds).2022.Machine Translation & Language Education:Implications for Theory,Research,& Practice.L2 Journal.
  • Koponen,Maarit,Salmi,Leena & Nikulin,Markku.2019.A product and process analysis of post-editor corrections on neural, statistical,and rule-based machine-translation output.Machine Translation 33,61–90.
  • Macketanz,Vivien,Avramidis,Eleftherios,Burchardt,Aljoscha,Helcl,Jindrich & Srivastava,Ankit.2017.Machine Translation:Phrase-Based,Rule-Based and Neural Approaches with
  • Linguistic Evaluation,Cybernetics and Information Technologies 17-2,28-43.
  • Maitland,Sara.2017.What is cultural translation?Bloomshory.
  • Kern,Rick.2024.Twenty-first century technologies and language education:Charting a path forward.The Modern Language Journal(in preparation).
  • Labarta Postigo,María.2020.A metaphorical map of subtitling.Idiom vs.explicit meaning in translated filmic texts.Babel 66(1),46-69.
  • Labarta Postigo,María.2021.¿Se te ha ido la olla? o ¿você é maluco?vs.are you (fucking nuts?La traducción de locuciones del inglés en series de TV por internet.Lengua y Habla 25,319-343.
  • Labarta Postigo,María.2022.El reto de las metáforas deportivas:Traducción automática vs.Traducción humana.Lengua y Habla 26:242–269.
  • Labarta Postigo,María.2023.‘Life is Baseball’ vs.‘A vida é futebol’:The Translation of Sport-Specific Metaphors from English to European and Brazilian Portuguese.Sendebar,34,1-15.
  • Lakoff,George & Johnson,Mark.1980.Metaphors We Live By.University of Chicago Press.
  • Lakoff,George.1993.The Contemporary Theory of Metaphor.In A. Ortony(Ed.),Metaphor and Thought(2nd ed.)202-251.Cambridge University Press.
  • Newmark,Peter.1988.A textbook of translation.Prentice Hall International.
  • Poibeau,Thierry.2017.Machine Translation.The MIT Press.
  • Shah,Priten.2023.AI and the Future of Education:Teaching in the Age of Artificial Intelligence.Jossey-Bass.
  • Trim,Richard.2007.Metaphor Networks.The Comparative Evolution of Figurative Language.Palgrave Macmillan.
Fuente de los datos: Dialnet