Skip to Main content Skip to Navigation
Conference papers

Semi-supervised experiments at LORIA for the SPMRL 2014 Shared Task

Christophe Cerisara 1, *
* Corresponding author
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : This paper describes the LORIA first participation at the SPMRL Shared Task. The focus of this work is on exploring several options to take advantage of the unlabeled data to improve the performances of a baseline dependency parser, which has neither be tuned to the specificities of the shared task nor evaluation languages. The semi-supervised approaches investigated include LDA word classes and super-tags predicted by a linear classifier trained with self-training. None of these options resulted in increased parsing accuracy.
Complete list of metadatas

Cited literature [32 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01109886
Contributor : Christophe Cerisara <>
Submitted on : Tuesday, January 27, 2015 - 10:44:04 AM
Last modification on : Tuesday, September 24, 2019 - 4:00:09 PM
Document(s) archivé(s) le : Tuesday, April 28, 2015 - 10:25:58 AM

File

Loria_28_Paper.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01109886, version 1

Collections

Citation

Christophe Cerisara. Semi-supervised experiments at LORIA for the SPMRL 2014 Shared Task. Proc. of the Shared Task on Statistical Parsing of Morphologically Rich Languages, Aug 2014, Dublin, Ireland. ⟨hal-01109886⟩

Share

Metrics

Record views

276

Files downloads

294