The Groupe d’Etudes pour la Traduction Automatique (GETA) is a research group founded by the late Professor B. Vauquois in 1971, and pursuing the work of the former CETA laboratory (1961-70). GETA’s methodology has been discussed extensively elsewhere [5, 6, 8, 20]. It revolves around three main facets: how to automate the translation process, what kind of linguistics to incorporate in the ‘lin...

Unknown words are a well-known hindrance to natural language applications. In particular, they drastically impact machine translation quality. An easy way out commercial translation systems usually offer their users is the possibility to add unknown words and their translations into a dedicated lexicon. Recently, (Stroppa et Yvon, 2005) shown how analogical learning alone deals nicely with morp...