Service interruption on Monday 11 July from 12:30 to 13:00: all the sites of the CCSD (HAL, EpiSciences, SciencesConf, AureHAL) will be inaccessible (network hardware connection).
Skip to Main content Skip to Navigation
Master Thesis

Approche mixte pour la traduction automatique statistique

Abstract : Machine Translation witnessed a major revolution in the area of natural language processing and the needs for reliable automatic machine translation systems increase. Therefore, we focused on the design of an automatic translation system based on statistical models. This work presents an improvement of the tuning and alignment of an existing statistical machine translation using a phrase-based approach for the Arabic/English language pair. We build also a new system based on hierarchical phrase-based approach. For this reason, we present the tools used in both systems. Finally, we present a qualitative and quantitative analyses of our different experiments that show first encouraging results.
Document type :
Master Thesis
Complete list of metadata

Cited literature [60 references]  Display  Hide  Download
Contributor : UGA - LLASIC Sciences du langage & FLES Connect in order to contact the contributor
Submitted on : Wednesday, July 21, 2010 - 3:51:10 PM
Last modification on : Sunday, March 14, 2021 - 9:54:03 PM
Long-term archiving on: : Thursday, December 1, 2016 - 5:16:42 PM


  • HAL Id : dumas-00504848, version 1


Haïtem Afli. Approche mixte pour la traduction automatique statistique. Linguistique. 2010. ⟨dumas-00504848⟩



Record views


Files downloads