Using subcategorization frames to improve French probabilistic parsing
Anthony Sigogne, Mathieu Constant · HAL (Le Centre pour la Communication Scientifique Directe) · 2012
This article introduces results about proba-bilistic parsing enhanced with a word clus-tering approach based on a French syntactic lexicon, the Lefff (Sagot, 2010). We show that by applying this clustering method on verbs and adjectives of the French Tree-bank (Abeille ́ et al., 2003), we obtain accurate performances on French with a parser based on a Probabilistic Context-Free Grammar (Petrov et al., 2006). 1