Discriminative phrase-based models for arabic machine translation

Cristina Espãa-Bonet, Jesús Giménez, Lluís Màrquez

Research output: Contribution to journalArticle

9 Citations (Scopus)


A design for an Arabic-to-English translation system is presented. The core of the system implements a standard phrase-based statistical machine translation architecture, but it is extended by incorporating a local discriminative phrase selection model to address the semantic ambiguity of Arabic. Local classifiers are trained using linguistic information and context to translate a phrase, and this significantly increases the accuracy in phrase selection with respect to the most frequent translation traditionally considered. These classifiers are integrated into the translation system so that the global task gets benefits from the discriminative learning. As a result, we obtain significant improvements in the full translation task at the lexical, syntactic, and semantic levels as measured by an heterogeneous set of automatic evaluation metrics.

Original languageEnglish
Article number15
JournalACM Transactions on Asian Language Information Processing
Issue number4
Publication statusPublished - 1 Dec 2009



  • Arabic
  • Discriminative learning
  • English
  • Statistical machine translation

ASJC Scopus subject areas

  • Computer Science(all)

Cite this