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

    SP - 56

    EP - 65

    ER -