Inférence de règles de propagation syntaxique pour l'alignement de mots

This paper presents and evaluates an original approach to automatically align bitexts at the word level. It relies on a syntactic dependency analysis of the texts and uses a machinelearning technique, namely inductive logic programming, to automatically infer rules called propagation rules. These rules make the most of the syntactic information to precisely align words. This approach is entirely automatic, uses very few training data, and its results rival the ones of the best existing alignment systems. Moreover, syntactic isomorphisms between the two spotted languages are easily identified through the inferred rules. MOTS-CLÉS : alignement de mots, apprentissage artificiel, programmation logique inductive, analyse syntaxique