Syntactic Parsing and Compound Recognition via Dual Decomposition: Application to French - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Syntactic Parsing and Compound Recognition via Dual Decomposition: Application to French

Résumé

In this paper we show how the task of syntactic parsing of non-segmented texts, including compound recognition, can be represented as constraints between phrase-structure parsers and CRF sequence labellers. In order to build a joint system we use dual decomposition, a way to combine several elementary systems which has proven successful in various NLP tasks. We evaluate this proposition on the French SPMRL corpus. This method compares favorably with pipeline architectures and improves state-of-the-art results.
Fichier non déposé

Dates et versions

hal-01074298 , version 1 (14-10-2014)

Identifiants

  • HAL Id : hal-01074298 , version 1

Citer

Joseph Le Roux, Mathieu Constant, Antoine Rozenknop. Syntactic Parsing and Compound Recognition via Dual Decomposition: Application to French. COLING 2014, the 25th International Conference on Computational Linguistics, Aug 2014, Dublin, Ireland. pp.1875-1885. ⟨hal-01074298⟩
160 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More