Cover not available
Article In:
Approaches to Machine Translation
Edited by Mahdieh Fakhar, Monica Vilhelm and Paz Díez-Arcón
[Translation and Translanguaging in Multilingual Contexts 11:1] 2025
► pp. 65–87

Google Translate versus DeepL in Spanish to English translation of Don Quixote

 | Universidad Nacional de Educación a Distancia (UNED)
 | Universidad Nacional de Educación a Distancia (UNED)
This paper analyses the effectiveness of neural machine translation when applied to literary translation and, more specifically, to the translation of collocations, one of the most difficult aspects in machine translation (Corpas-Pastor 2015; Shraiden and Mahadin 2015). Literary translation continues to constitute one of the biggest challenges for machine translation (Toral and Way 2018), where cohesion errors are amongst the most frequent (Voigt and Jurafsky 2012). A comparative analysis of the translation of the first chapter of the world literature masterpiece El ingenioso hidalgo don Quijote de la Mancha — known as Don Quixote in English — was carried out, paying close attention to collocations. The human translation done by Tom Lathrop (Don Quixote)
was compared to the target texts obtained with the two biggest neural machine translation systems today, Google Translate and DeepL, to see which provided more accurate results. The results confirm that neural machine translation offers highly reliable results. On a quantitative level the margins are very narrow when determining which system, DeepL or Google Translate, is better. DeepL scored better in terms of accuracy and recall, but in the BLEU metrics Google Translate scored 28.10 and DeepL 26.63. On a qualitative level and from a subjective point of view, we found DeepL’s translation to be somewhat more fluid and natural than Google Translate’s.
Keywords: literary translation, neural machine translation, collocations
Article outline
  • 1.Introduction
  • 2.Theoretical framework
    • 2.1Literary translation
    • 2.2Machine translation and its application in literary texts
  • 3.State of the art
  • 4.Methodology
    • 4.1Methodological procedures
    • 4.2Tools for the analysis
  • 5.Corpus
    • 5.1Selection of collocations from Chapter I of Don Quixote
    • 5.2Tom Lathrop’s translation strategies
  • 6.Results and analysis
    • 6.1Qualitative analysis
    • 6.2Quantitative analysis
  • 7.Conclusions
  • Notes
  • References
This content is being prepared for publication; it may be subject to changes.
References (23)
References
Allen, Esther, Mary Ann Caws, Peter Constantine, Edith Grosman, Nancy Kline, Burton Pike, Damian Searls, Karen Van Dyck, Alyson Waters, Alyson, Roger Celestin, and Charles LeBel. 2015. “Lost in Translation? Found in Translation? Neither? Both?.” The Quiet Corner Interdisciplinary Journal 1 (1): 7. [URL]
Barbieri, Alberto. 2019. “Traductores e intérpretes, ¿las próximas víctimas de la inteligencia artificial?.” La Vanguardia, June 1st. [URL]
Bernardini, Silvia. 2007. “Collocations in Translated Language. Combining Parallel, Comparable and Reference Corpora. UCREL Corpus Research Center.” [URL]
Bosque, Ignacio. 2006. Diccionario combinatorio práctico del español contemporáneo. Madrid: Ediciones SM.Google Scholar
Cervantes Saavedra, Miguel de. 1605. El ingenioso hidalgo Don Quixote de la Mancha. Madrid: Juan de la Cuesta.Google Scholar
De Aguiar e Silva, Víctor Manuel. 1986. Teoría de la literatura. Madrid: Gredos.Google Scholar
Díaz Prieto, Petra. 2012. Luces y sombras en los 75 años de traducción automática. León: Universidad de León.Google Scholar
Firth, John Rupert. 1957. Papers in Linguistics 1934–1951. London: London University Press.Google Scholar
Grossman, Edith. 2010. Why Translation Matters. Yale: Yale University Press.Google Scholar
Hurtado Albir, Amparo. 2018. Traducción y traductología. Introducción a la traductología. Madrid: Cátedra.Google Scholar
McCarthy, Michael. 1990. Vocabulary. Oxford: Oxford University Press.Google Scholar
Punga, Loredana, and Hortensia Pârlog. 2017. “Difficulties of Translating English Collocations into Romanian.” BAS: a Journal of the Romanian Society of English and American Studies XXIII1: 256–274.Google Scholar
Rubio, Isabel. 2019. “El ingeniero que te permite hablar más de 100 idiomas.” El País, November 25th. [URL]
. 2020. “¿Cuál es el mejor traductor?: probamos DeepL, Google Translate y Bing.” El País, May 29th. [URL]
Sánchez Pérez, Aquilino. 2010. “Traducción automática, corpus lingüísticos y desambiguación automática de los significados de las palabras.” Lengua, traducción, recepción: en honor de Julio César Santoyo 11: 555–587.Google Scholar
Serrano, Rocío. 2020. “Traducción automática y literatura: ¿enemigas íntimas?.” Vasos Comunicantes. Revista de ACE Traductores 541. [URL]
Shiyab, Said, and Michael Stuart Lynch. 2006. “Can Literary Style be Translated?.” Babel 52(3): 262–275. DOI logoGoogle Scholar
Shraiden, Khetam, and Radwam Salim Mahadin. 2015. “Difficulties and Strategies in Translating Collocations in BBC Political Texts.” Arab World English Journal (AWEJ) 6(3): 320–356. DOI logoGoogle Scholar
Toral, Antonio, and Andy Way. 2018. “What Level of Quality Can Neural Machine Translation Attain on Literary Text?.” In Translation Quality Assessment. Machine Translation: Technologies and Applications, ed. by Joos Moorkens, Sheila Castilho, Federico Gaspari, and Stephen Doherty, 263–287. Dublin: Springer, Cham. DOI logoGoogle Scholar
Venegas, René. 2003. “Análisis Semántico Latente: una panorámica de su desarrollo.” Revista Signos 36(53): 121–138. DOI logoGoogle Scholar
Vielma Vinci, Nathalie. 2020. “DeepL: una combinación exitosa entre redes neuronales y datos de calidad.” [URL]
Voigt, Rob, and Dan Jurafsky. 2012. “Towards a Literary Machine Translation: The Role of Referencial Cohesion.” In Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature, ed. by David Elson, Anna Kazantseva, Rada Mihalcea, and Stan Szpakowicz, 18–25. Montréal, Canada: Association for Computational Linguistics.Google Scholar