Section: New Results

Automatic tools for developping, improving and correcting lexical resources

Participants : Benoît Sagot, Éric Villemonte de La Clergerie.

Collaboration with Lionel Nicolas (University of Nice) and Miguel Ángel Molinero Álvarez (University of Ourense, Galicia, Spain).

In collaboration with Lionel Nicolas (University of Nice) and Miguel Ángel Molinero Álvarez (University of Ourense, Galicia, Spain), within the Victoria project funded by the government of Galicia [53] , [33] , we worked towards the development of a more complete lexical development framework that is able to detect missing and dubious entries in existing lexicons with different techniques, and suggest respectively addition and corrections hypotheses for these entries. This is achieved thanks to two different techniques; the first one is based on a specific statistical model, the other one benefits from information given by a part-of-speech tagger. The generation of correction hypotheses for dubious lexical entries is achieved by studying which modifications could improve the successful parse rate of sentences in which they occur. This process brings together various techniques based on different tools such as taggers, parsers and statistical models [34] , [35] .

We applied this technique for improving the Leff e, an Alexina lexicon for Spanish (see  6.7 ).