CAN CAT TOOLS AND LARGE LANGUAGE MODELS TRANSLATE FROM UNRECOGNISED LANGUAGES?
DOI:
https://doi.org/10.33919/JCAL.24.2.5Keywords:
gisting translation, translating ancient languages, computer-aided translation of Latin, machine translationAbstract
First designed as a case study for high-school students competing in the field of linguistics, this experiment is based on the hypothesis that CAT tools and large language models have arrived at a stage where they can translate texts from languages that have not been explicitly listed as source languages. We took an excerpt in old French ancien français from Chrétien de Troyes’s novel Le Chevalier de la Charrette, versified into octosyllables. We machine translated it into Bulgarian – first from Latin and French with Phrase, and then without specifying the source language with ChatGPT. Phrase yielded better results with Latin than with modern French. Still, ChatGPT’s translation was much better and could be considered as a gisting translation. We had a reference human translation – into modern French, non versified, and into Bulgarian, versified. When comparing the results, we found that Phrase couldn’t provide a gisting translation, while ChatGPT rendered the general events and characters present in the text, even though on a contextual level there were still a lot of discrepancies; detail was missing; the text was rendered in prose. The experiment was conclusive that LLMs manage to render the general meaning of a text from an unknown dead language. It was illustrative for the students who were introduced to the specificities of medieval French and were given some linguistics problems to solve, based on the particularities of this language and its versification. The experiment shows the extent to which cultural heritage such as medieval knights’ novels can be rendered accessible to modern-day public, without having to resort to
professional translation.
References
Bougy, C. (2007). ‘Les « pseudo-adverbes » concessifs neporuec, neporquant, nequedent et l’adverbe toute(s)voie(s) en ancien français’. Syntaxe sémantique, Issue 8, 107–124.
Cerquiglini, B. (1993). La naissance du français. 2nd edition. Paris: Presses Universitaires de France.
Gaspar, C. (2020). ‘Orthography as Described in Latin Grammars and Spelling in Latin Epigraphic Texts’. Acta Classica Universitatis Scientiarum Debreceniensis, Issue 56, 61–72.
Lacy, N. J. (1991). ‘Chrétien de Troyes’. In: N. J. Lacy. The New Arthurian Encyclopedia. New York: Garland, 88–91.
Lodge, R. A. (1993). French: From Dialect to Standard. London: Routledge.
Pellegrini, G. B. (1980). ‘Substrata’. In: R. Posner, J. N. Green, eds. Trends in Romance Linguistics and Philology. Volume 1: Romance Comparative and Historical Linguistics.The Hague: Mouton, 43–72.
Roegiest, E. (2006). Vers les sources des langues romanes: Un itinéraire linguistique à travers la Romania. Leuven: Acco.
Uitti, K. D. (1995). Chrétien de Troyes Revisited. New York: Twayne Publishers.
Verma, S., Gupta, N., B C, A., Chauhan, R. (2023). ‘A Novel Framework for Ancient Text Translation Using Artificial Intelligence’. Advances in Distributed Computing and Artificial Intelligence Journal, 11(4), 411–425.
