Improving a symbolic parser through partially supervised learning

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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/hal-00879358
Contributor : Eric Villemonte de La Clergerie <>
Submitted on : Saturday, November 2, 2013 - 10:58:38 PM
Last modification on : Thursday, February 7, 2019 - 3:01:58 PM
Document(s) archivé(s) le : Monday, February 3, 2014 - 4:26:54 AM

File

mgconll.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00879358, version 1

Collections

Citation

Éric Villemonte de La Clergerie. Improving a symbolic parser through partially supervised learning. The 13th International Conference on Parsing Technologies (IWPT), Nov 2013, Naria, Japan. ⟨hal-00879358⟩

Share

Metrics

Record views

303

Files downloads

152