Improving a symbolic parser through partially supervised learning

Reference ID6366
TitreImproving a symbolic parser through partially supervised learning
Publication TypeConference Paper
Année de publication2013
AuteursDe La Clergerie, ÉVillemonte
Nom de la conférenceThe 13th International Conference on Parsing Technologies (IWPT)
Lieu de la conférenceNara, Japon
Mots-clésparsing, partially supervised machine learning, statitistical parsing, symbolic parsing, Tree Adjoining Grammar
Abstract

Recently, several statistical parsers have been trained and evaluated on the dependency version of the French TreeBank (FTB). However, older symbolic parsers still exist, including FRMG, a wide coverage TAG parser. It is interesting to compare these different parsers, based on very different approaches, and explore the possibilities of hybridization. In particular, we explore the use of partially supervised learning techniques to improve the performances of FRMG to the levels reached by the statistical parsers.

URLhttp://hal.inria.fr/hal-00879358
Texte complet