Translating Medieval Texts with the Help of AI: The Case of the "General estoria" (1) into Modern French

Abstract

This study analyzes the functioning of artificial intelligence (AI) in the translation from medieval Spanish to modern academic French from a philological and translation studies perspective. Its main objective is to demonstrate that AI does not translate through automatic lexical substitutions, but rather through operations of segmentation, disambiguation, syntactic reconstruction, and the identification of functional equivalents. To this end, it examines the translation of a short passage from the General estoria (I), focusing on historical orthographic forms, the semantic density of the lexicon, the moral and religious connotations of the discourse, and the reorganization of the sentence in the target language. The study also considers the main areas of interpretive risk, proposes a typology of frequent errors and quality control criteria, and reflects on the scope and relative reproducibility of the results.