<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dyer-2007-university">
    <titleInfo>
        <title>The University of Maryland translation system for IWSLT 2007</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Christopher</namePart>
        <namePart type="given">J</namePart>
        <namePart type="family">Dyer</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2007-oct 15-16</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Fourth International Workshop on Spoken Language Translation</title>
        </titleInfo>
        <originInfo>
            <place>
                <placeTerm type="text">Trento, Italy</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper describes the University of Maryland statistical machine translation system used in the IWSLT 2007 evaluation. Our focus was threefold: using hierarchical phrase-based models in spoken language translation, the incorporation of sub-lexical information in model estimation via morphological analysis (Arabic) and word and character segmentation (Chinese), and the use of n-gram sequence models for source-side punctuation prediction. Our efforts yield significant improvements in Chinese-English and Arabic-English translation tasks for both spoken language and human transcription conditions.</abstract>
    <identifier type="citekey">dyer-2007-university</identifier>
    <location>
        <url>https://aclanthology.org/2007.iwslt-1.28</url>
    </location>
    <part>
        <date>2007-oct 15-16</date>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T The University of Maryland translation system for IWSLT 2007
%A Dyer, Christopher J.
%S Proceedings of the Fourth International Workshop on Spoken Language Translation
%D 2007
%8 oct 15 16
%C Trento, Italy
%F dyer-2007-university
%X This paper describes the University of Maryland statistical machine translation system used in the IWSLT 2007 evaluation. Our focus was threefold: using hierarchical phrase-based models in spoken language translation, the incorporation of sub-lexical information in model estimation via morphological analysis (Arabic) and word and character segmentation (Chinese), and the use of n-gram sequence models for source-side punctuation prediction. Our efforts yield significant improvements in Chinese-English and Arabic-English translation tasks for both spoken language and human transcription conditions.
%U https://aclanthology.org/2007.iwslt-1.28

Markdown (Informal)

[The University of Maryland translation system for IWSLT 2007](https://aclanthology.org/2007.iwslt-1.28) (Dyer, IWSLT 2007)

• The University of Maryland translation system for IWSLT 2007 (Dyer, IWSLT 2007)

ACL

• Christopher J. Dyer. 2007. The University of Maryland translation system for IWSLT 2007. In Proceedings of the Fourth International Workshop on Spoken Language Translation, Trento, Italy.