Using subcategorization frames to improve French probabilistic parsing

Anthony Sigogne (1) , Mathieu Constant (1)

1 LIGM - Laboratoire d'Informatique Gaspard-Monge

This article introduces results about probabilistic parsing enhanced with a word clustering approach based on a French syntactic lexicon, the Lefff. We show that by applying this clustering method on verbs and adjectives of the French Treebank, we obtain accurate performances on French with a parser based on a Probabilistic Context-Free Grammar.

Domaines: Traitement du texte et du document

Anthony Sigogne, Mathieu Constant. Using subcategorization frames to improve French probabilistic parsing. 11th Conference on Natural Language Processing (KONVENS'12), Sep 2012, Austria. pp.223-227. ⟨hal-00790629⟩