<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanchis-trilles-etal-2009-online">
    <titleInfo>
        <title>Online language model adaptation for spoken dialog translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Germán</namePart>
        <namePart type="family">Sanchis-Trilles</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mauro</namePart>
        <namePart type="family">Cettolo</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>
    <name type="personal">
        <namePart type="given">Marcello</namePart>
        <namePart type="family">Federico</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2009-dec 1-2</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 6th International Workshop on Spoken Language Translation: Papers</title>
        </titleInfo>
        <originInfo>
            <place>
                <placeTerm type="text">Tokyo, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper focuses on the problem of language model adaptation in the context of Chinese-English cross-lingual dialogs, as set-up by the challenge task of the IWSLT 2009 Evaluation Campaign. Mixtures of n-gram language models are investigated, which are obtained by clustering bilingual training data according to different available human annotations, respectively, at the dialog level, turn level, and dialog act level. For the latter case, clustering of IWSLT data was in fact induced through a comparable Italian-English parallel corpus provided with dialog act annotations. For the sake of adaptation, mixture weight estimation is performed either at the level of single source sentence or test set. Estimated weights are then transferred to the target language mixture model. Experimental results show that, by training different specific language models weighted according to the actual input instead of using a single target language model, significant gains in terms of perplexity and BLEU can be achieved.</abstract>
    <identifier type="citekey">sanchis-trilles-etal-2009-online</identifier>
    <location>
        <url>https://aclanthology.org/2009.iwslt-papers.5</url>
    </location>
    <part>
        <date>2009-dec 1-2</date>
        <extent unit="page">
            <start>160</start>
            <end>167</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Online language model adaptation for spoken dialog translation
%A Sanchis-Trilles, Germán
%A Cettolo, Mauro
%A Bertoldi, Nicola
%A Federico, Marcello
%S Proceedings of the 6th International Workshop on Spoken Language Translation: Papers
%D 2009
%8 dec 1 2
%C Tokyo, Japan
%F sanchis-trilles-etal-2009-online
%X This paper focuses on the problem of language model adaptation in the context of Chinese-English cross-lingual dialogs, as set-up by the challenge task of the IWSLT 2009 Evaluation Campaign. Mixtures of n-gram language models are investigated, which are obtained by clustering bilingual training data according to different available human annotations, respectively, at the dialog level, turn level, and dialog act level. For the latter case, clustering of IWSLT data was in fact induced through a comparable Italian-English parallel corpus provided with dialog act annotations. For the sake of adaptation, mixture weight estimation is performed either at the level of single source sentence or test set. Estimated weights are then transferred to the target language mixture model. Experimental results show that, by training different specific language models weighted according to the actual input instead of using a single target language model, significant gains in terms of perplexity and BLEU can be achieved.
%U https://aclanthology.org/2009.iwslt-papers.5
%P 160-167

Markdown (Informal)

[Online language model adaptation for spoken dialog translation](https://aclanthology.org/2009.iwslt-papers.5) (Sanchis-Trilles et al., IWSLT 2009)

• Online language model adaptation for spoken dialog translation (Sanchis-Trilles et al., IWSLT 2009)

ACL

• Germán Sanchis-Trilles, Mauro Cettolo, Nicola Bertoldi, and Marcello Federico. 2009. Online language model adaptation for spoken dialog translation. In Proceedings of the 6th International Workshop on Spoken Language Translation: Papers, pages 160–167, Tokyo, Japan.