Skip to Main content Skip to Navigation
Master Thesis

Outils génériques pour l'étiquetage morphosyntaxique de la langue arabe : segmentation et corpus d'entraînement

Abstract : The main goal of this study is the implementation of a new tool for the part-ofspeech tagging of Arabic. After studying the different approaches and problems of arabic tagging, we implemented a tagging system based on TreeTagger, a generic stochastic tagging tool, very popular for its efficiency. First of all, we began by gathering a working corpus, large enough to ensure a general linguistic coverage. This corpus has been used to implement the tokenization process, as well as to train Treetagger. We first present our method of tokenization, then we describe all the steps of the preprocessing and training process, using ASVM 1.0 to yield a raw POS tagging that was subsequently manually corrected. Finally, we implemented a straightfoward evaluation of the outputs, both in a quantitative and qualitative way, on a small test corpus. Though restricted, this evaluation showed really encouraging results.
Document type :
Master Thesis
Complete list of metadata

Cited literature [24 references]  Display  Hide  Download

https://dumas.ccsd.cnrs.fr/dumas-00631517
Contributor : Uga - Bulles <>
Submitted on : Wednesday, October 12, 2011 - 3:43:19 PM
Last modification on : Sunday, March 14, 2021 - 9:54:03 PM
Long-term archiving on: : Friday, January 13, 2012 - 3:10:41 AM

Identifiers

  • HAL Id : dumas-00631517, version 1

Citation

Dhaou Ghoul. Outils génériques pour l'étiquetage morphosyntaxique de la langue arabe : segmentation et corpus d'entraînement. Linguistique. 2011. ⟨dumas-00631517⟩

Share

Metrics

Record views

967

Files downloads

4485