Generative Constituent Parsing and Discriminative Dependency Reranking: Experiments on English and French

Joseph Le Roux (1) , Benoit Favre (2, 3) , Alexis Nasr (2) , Seyed Abolghasem Mirroshandel (2)

1 LIPN - Laboratoire d'Informatique de Paris-Nord
2 LIF - Laboratoire d'informatique Fondamentale de Marseille - UMR 6166
3 TALEP - Traitement Automatique du Langage Ecrit et Parlé

We present an architecture for parsing in two steps. A phrase-structure parser builds for each sentence an n-best list of analyses which are converted to dependency trees. These de- pendency structures are then rescored by a dis- criminative reranker. Our method is language agnostic and enables the incorporation of ad- ditional information which are useful for the choice of the best parse candidate. We test our approach on the the Penn Treebank and the French Treebank. Evaluation shows a sig- nificative improvement on different parse met- rics.

Domaines: Informatique et langage [cs.CL]

Joseph Le Roux, Benoit Favre, Alexis Nasr, Seyed Abolghasem Mirroshandel. Generative Constituent Parsing and Discriminative Dependency Reranking: Experiments on English and French. ACL 2012 Joint Workshop on Statistical Parsing and Semantic Processing of Morphologically Rich Languages (SP-Sem-MRL 2012), 2012, Jesu Island, South Korea. ⟨hal-00702499⟩