Discriminative phrase-based models for arabic machine translation

Cristina Espãa-Bonet, Jesús Giménez, Lluis Marques

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

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
Volume8
Issue number4
DOIs
Publication statusPublished - 1 Dec 2009
Externally publishedYes

Fingerprint

Classifiers
Semantics
Syntactics
Linguistics

Keywords

  • Arabic
  • Discriminative learning
  • English
  • Statistical machine translation

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Discriminative phrase-based models for arabic machine translation. / Espãa-Bonet, Cristina; Giménez, Jesús; Marques, Lluis.

In: ACM Transactions on Asian Language Information Processing, Vol. 8, No. 4, 15, 01.12.2009.

Research output: Contribution to journalArticle

@article{f79fb78eb2134244bc907b9f612b7ae7,
title = "Discriminative phrase-based models for arabic machine translation",
abstract = "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.",
keywords = "Arabic, Discriminative learning, English, Statistical machine translation",
author = "Cristina Esp{\~a}a-Bonet and Jes{\'u}s Gim{\'e}nez and Lluis Marques",
year = "2009",
month = "12",
day = "1",
doi = "10.1145/1644879.1644882",
language = "English",
volume = "8",
journal = "ACM Transactions on Asian Language Information Processing",
issn = "1530-0226",
publisher = "Association for Computing Machinery (ACM)",
number = "4",

}

TY - JOUR

T1 - Discriminative phrase-based models for arabic machine translation

AU - Espãa-Bonet, Cristina

AU - Giménez, Jesús

AU - Marques, Lluis

PY - 2009/12/1

Y1 - 2009/12/1

N2 - 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.

AB - 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.

KW - Arabic

KW - Discriminative learning

KW - English

KW - Statistical machine translation

UR - http://www.scopus.com/inward/record.url?scp=75649145317&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=75649145317&partnerID=8YFLogxK

U2 - 10.1145/1644879.1644882

DO - 10.1145/1644879.1644882

M3 - Article

VL - 8

JO - ACM Transactions on Asian Language Information Processing

JF - ACM Transactions on Asian Language Information Processing

SN - 1530-0226

IS - 4

M1 - 15

ER -