This study presents a comparative analysis of the translations of the opening tercet of Dante’s Inferno, produced by two state-of-theart systems, that is Google Translate and ChatGPT-4o, and four translations by distinguished scholars and poets spanning from the 19th to the early 21st century. By integrating human evaluation, conducted via an online questionnaire, with the COMET automatic metric, this research seeks to explore the extent to which machine translation systems can effectively render the linguistic and stylistic nuances of one of the most iconic works in literary history.
Sprugnoli, R., AI Meets Dante: Evaluating Machine Translation Applied to the First Tercet of the Divine Comedy, in Domenico Giuseppe Muscianis, D. G. M. (ed.), Rapsodie dantesche. L’incipit della Commedia e le sue traduzioni, Uninova, Parma 2025: 161- 177 [https://hdl.handle.net/10807/350979]
AI Meets Dante: Evaluating Machine Translation Applied to the First Tercet of the Divine Comedy
Sprugnoli, Rachele
Primo
2025
Abstract
This study presents a comparative analysis of the translations of the opening tercet of Dante’s Inferno, produced by two state-of-theart systems, that is Google Translate and ChatGPT-4o, and four translations by distinguished scholars and poets spanning from the 19th to the early 21st century. By integrating human evaluation, conducted via an online questionnaire, with the COMET automatic metric, this research seeks to explore the extent to which machine translation systems can effectively render the linguistic and stylistic nuances of one of the most iconic works in literary history.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
