Challenges in building an Arabic-English GHMT system with SMT components

Nizar Habash, Bonnie Dorr, Christof Monz

Research output: Contribution to conferencePaper

Abstract

The research context of this paper is developing hybrid machine translation (MT) systems that exploit the advantages of linguistic rule-based and statistical MT systems. Arabic, as a morphologically rich language, is especially challenging even without addressing the hybridization question. In this paper, we describe the challenges in building an Arabic- English generation-heavy machine translation (GHMT) system and boosting it with statistical machine translation (SMT) components. We present an extensive evaluation of multiple system variants and report positive results on the advantages of hybridization.

Original languageEnglish (US)
Pages56-65
Number of pages10
StatePublished - Dec 1 2006
Event7th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2006 - Cambridge, MA, United States
Duration: Aug 8 2006Aug 12 2006

Other

Other7th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2006
CountryUnited States
CityCambridge, MA
Period8/8/068/12/06

Fingerprint

Linguistics
Machine Translation System
Statistical Machine Translation
Hybridization
Evaluation
Language

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Software

Cite this

Habash, N., Dorr, B., & Monz, C. (2006). Challenges in building an Arabic-English GHMT system with SMT components. 56-65. Paper presented at 7th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2006, Cambridge, MA, United States.

Challenges in building an Arabic-English GHMT system with SMT components. / Habash, Nizar; Dorr, Bonnie; Monz, Christof.

2006. 56-65 Paper presented at 7th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2006, Cambridge, MA, United States.

Research output: Contribution to conferencePaper

Habash, N, Dorr, B & Monz, C 2006, 'Challenges in building an Arabic-English GHMT system with SMT components' Paper presented at 7th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2006, Cambridge, MA, United States, 8/8/06 - 8/12/06, pp. 56-65.
Habash N, Dorr B, Monz C. Challenges in building an Arabic-English GHMT system with SMT components. 2006. Paper presented at 7th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2006, Cambridge, MA, United States.
Habash, Nizar ; Dorr, Bonnie ; Monz, Christof. / Challenges in building an Arabic-English GHMT system with SMT components. Paper presented at 7th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2006, Cambridge, MA, United States.10 p.
@conference{a2b45bb3f3cc412c9a5c24d17ed39c23,
title = "Challenges in building an Arabic-English GHMT system with SMT components",
abstract = "The research context of this paper is developing hybrid machine translation (MT) systems that exploit the advantages of linguistic rule-based and statistical MT systems. Arabic, as a morphologically rich language, is especially challenging even without addressing the hybridization question. In this paper, we describe the challenges in building an Arabic- English generation-heavy machine translation (GHMT) system and boosting it with statistical machine translation (SMT) components. We present an extensive evaluation of multiple system variants and report positive results on the advantages of hybridization.",
author = "Nizar Habash and Bonnie Dorr and Christof Monz",
year = "2006",
month = "12",
day = "1",
language = "English (US)",
pages = "56--65",
note = "7th Biennial Conference of the Association for Machine Translation in the Americas, AMTA 2006 ; Conference date: 08-08-2006 Through 12-08-2006",

}

TY - CONF

T1 - Challenges in building an Arabic-English GHMT system with SMT components

AU - Habash, Nizar

AU - Dorr, Bonnie

AU - Monz, Christof

PY - 2006/12/1

Y1 - 2006/12/1

N2 - The research context of this paper is developing hybrid machine translation (MT) systems that exploit the advantages of linguistic rule-based and statistical MT systems. Arabic, as a morphologically rich language, is especially challenging even without addressing the hybridization question. In this paper, we describe the challenges in building an Arabic- English generation-heavy machine translation (GHMT) system and boosting it with statistical machine translation (SMT) components. We present an extensive evaluation of multiple system variants and report positive results on the advantages of hybridization.

AB - The research context of this paper is developing hybrid machine translation (MT) systems that exploit the advantages of linguistic rule-based and statistical MT systems. Arabic, as a morphologically rich language, is especially challenging even without addressing the hybridization question. In this paper, we describe the challenges in building an Arabic- English generation-heavy machine translation (GHMT) system and boosting it with statistical machine translation (SMT) components. We present an extensive evaluation of multiple system variants and report positive results on the advantages of hybridization.

UR - http://www.scopus.com/inward/record.url?scp=71249102370&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71249102370&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:71249102370

SP - 56

EP - 65

ER -