<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="federico-bertoldi-2012-practical">
    <titleInfo>
        <title>Practical Domain Adaptation in SMT</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Marcello</namePart>
        <namePart type="family">Federico</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nicola</namePart>
        <namePart type="family">Bertoldi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2012-oct 28-nov 1</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Tutorials</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Machine Translation in the Americas</publisher>
            <place>
                <placeTerm type="text">San Diego, California, USA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Several studies have recently reported significant productivity gains by human translators when besides translation memory (TM) matches they do also receive suggestions from a statistical machine translation (SMT) engine. In fact, an increasing number of language service providers and in-house translation services of large companies is nowadays integrating SMT in their workflow. The technology transfer of state-of-the-art SMT technology from research to industry has been relatively fast and simple also thanks to development of open source software, such as MOSES, GIZA++, and IRSTLM. While a translator is working on a specific translation project, she evaluates the utility of translating versus post-editing a segment based on the adequacy and fluency provided by the SMT engine, which in turn depends on the considered language pair, linguistic domain of the task, and the amount of available training data. Statistical models, like those employed in SMT, rely on a simple assumption: data used to train and tune the models represent the target translation task. Unfortunately, this assumption cannot be satisfied for most of the real application cases, simply because for most of the language pairs and domains there is no sufficient data to adequately train an SMT system. Hence, common practice is to train SMT systems by merging together parallel and monolingual data from the target domain with as much as possible data from any other available source. This workaround is simple and gives practical benefits but is often not the best way to exploit the available data. This tutorial copes with the optimal use of in-domain and out-of-domain data to achieve better SMT performance on a given application domain. Domain adaptation, in general, refers to statistical modeling and machine learning techniques that try to cope with the unavoidable mismatch between training and task data that typically occurs in real life applications. Our tutorial will survey several application cases in which domain adaptation can be applied, and presents adaptation techniques that best fit each case. In particular, we will cover adaptation methods for n-gram language models and translation models in phrase-based SMT. The tutorial will provide some high-level theoretical background in domain adaptation, it will discuss practical application cases, and finally show how the presented methods can be applied with two widely used software tools: Moses and IRSTLM. The tutorial is suited for any practitioner of statistical machine translation. No particular programming or mathematical background is required.</abstract>
    <identifier type="citekey">federico-bertoldi-2012-practical</identifier>
    <location>
        <url>https://aclanthology.org/2012.amta-tutorials.6</url>
    </location>
    <part>
        <date>2012-oct 28-nov 1</date>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Practical Domain Adaptation in SMT
%A Federico, Marcello
%A Bertoldi, Nicola
%S Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Tutorials
%D 2012
%8 oct 28 nov 1
%I Association for Machine Translation in the Americas
%C San Diego, California, USA
%F federico-bertoldi-2012-practical
%X Several studies have recently reported significant productivity gains by human translators when besides translation memory (TM) matches they do also receive suggestions from a statistical machine translation (SMT) engine. In fact, an increasing number of language service providers and in-house translation services of large companies is nowadays integrating SMT in their workflow. The technology transfer of state-of-the-art SMT technology from research to industry has been relatively fast and simple also thanks to development of open source software, such as MOSES, GIZA++, and IRSTLM. While a translator is working on a specific translation project, she evaluates the utility of translating versus post-editing a segment based on the adequacy and fluency provided by the SMT engine, which in turn depends on the considered language pair, linguistic domain of the task, and the amount of available training data. Statistical models, like those employed in SMT, rely on a simple assumption: data used to train and tune the models represent the target translation task. Unfortunately, this assumption cannot be satisfied for most of the real application cases, simply because for most of the language pairs and domains there is no sufficient data to adequately train an SMT system. Hence, common practice is to train SMT systems by merging together parallel and monolingual data from the target domain with as much as possible data from any other available source. This workaround is simple and gives practical benefits but is often not the best way to exploit the available data. This tutorial copes with the optimal use of in-domain and out-of-domain data to achieve better SMT performance on a given application domain. Domain adaptation, in general, refers to statistical modeling and machine learning techniques that try to cope with the unavoidable mismatch between training and task data that typically occurs in real life applications. Our tutorial will survey several application cases in which domain adaptation can be applied, and presents adaptation techniques that best fit each case. In particular, we will cover adaptation methods for n-gram language models and translation models in phrase-based SMT. The tutorial will provide some high-level theoretical background in domain adaptation, it will discuss practical application cases, and finally show how the presented methods can be applied with two widely used software tools: Moses and IRSTLM. The tutorial is suited for any practitioner of statistical machine translation. No particular programming or mathematical background is required.
%U https://aclanthology.org/2012.amta-tutorials.6

Markdown (Informal)

[Practical Domain Adaptation in SMT](https://aclanthology.org/2012.amta-tutorials.6) (Federico & Bertoldi, AMTA 2012)

• Practical Domain Adaptation in SMT (Federico & Bertoldi, AMTA 2012)

ACL

• Marcello Federico and Nicola Bertoldi. 2012. Practical Domain Adaptation in SMT. In Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Tutorials, San Diego, California, USA. Association for Machine Translation in the Americas.