Modélisation lexicale et intelligence artificielle : une ressource bilingue pour l’architecture contemporaine

Abstract

This article presents a methodology for the design of a bilingual French-Spanish lexical resource dedicated to contemporary architecture, a field characterized by a constantly evolving terminology and a lack of specialized dictionaries. Our proposal is based on a model that integrates the entire lexicographic workflow – from corpus building to final encoding, including extraction, alignment, definition, and enrichment – while leveraging the contributions of artificial intelligence. Statistical and neural models are used to automate steps that are traditionally lengthy and demanding – such as term identification, semantic clustering, draft definition generation, or the detection of variants. However, this automation remains framed by systematic human validation, which is indispensable to ensure conceptual accuracy and terminological consistency. More broadly, our methodology provides a roadmap that can be applied to other specialized domains and to under-represented languages.