Nicolas Stroppa

Learn More
Basque is both a minority and a highly inflected language with free order of sentence constituents. Machine Translation of Basque is thus both a real need and a test bed for MT techniques. In this paper, we present a modular Data-Driven MT system which includes different chunkers as well as chunk aligners which can deal with the free order of sentence(More)
In this paper, we compare the rule­based and data­driven approaches in the context of Spanish­to­Basque Machine Translation. The rule­based system we consider has been developed specifically for Spanish­to­Basque machine translation, and is tuned to this language pair. On the contrary, the data­driven system we use is generic, and has not been specifically(More)
Function labels enrich constituency parse tree nodes with information about their abstract syntactic and semantic roles. A common way to obtain function-labeled trees is to use a two-stage architecture where first a statistical parser produces the constituent structure and then a second component such as a classifier adds the missing function tags. In order(More)
Apprentissage par analogie et proportions formelles : définitions et aspects méthodologiques Résumé L'apprentissage par analogie exploite un mécanisme inductif en deux étapes consistant à : (i) construire un appariement entre une nouvelle situation et des situations déjà connues ; (ii) transférer partiellement des propriétés de la situation analogue vers la(More)
We present an analogical learning model which exploits the notion of formal analogi-cal proportions; this approach requires the ability to define these proportions and to implement them efficiently. We propose an algebraic definition of this notion, which applies to a large range of structured objects: words, attribute-value structures, labeled trees. We(More)