<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="do-etal-2014-discriminative">
    <titleInfo>
        <title>Discriminative adaptation of continuous space translation models</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Quoc-Khanh</namePart>
        <namePart type="family">Do</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Alexandre</namePart>
        <namePart type="family">Allauzen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">François</namePart>
        <namePart type="family">Yvon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2014-dec 4-5</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 11th International Workshop on Spoken Language Translation: Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marcello</namePart>
            <namePart type="family">Federico</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sebastian</namePart>
            <namePart type="family">Stüker</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">François</namePart>
            <namePart type="family">Yvon</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <place>
                <placeTerm type="text">Lake Tahoe, California</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>In this paper we explore various adaptation techniques for continuous space translation models (CSTMs). We consider the following practical situation: given a large scale, state-of-the-art SMT system containing a CSTM, the task is to adapt the CSTM to a new domain using a (relatively) small in-domain parallel corpus. Our method relies on the definition of a new discriminative loss function for the CSTM that borrows from both the max-margin and pair-wise ranking approaches. In our experiments, the baseline out-of-domain SMT system is initially trained for the WMT News translation task, and the CSTM is to be adapted to the lecture translation task as defined by IWSLT evaluation campaign. Experimental results show that an improvement of 1.5 BLEU points can be achieved with the proposed adaptation method.</abstract>
    <identifier type="citekey">do-etal-2014-discriminative</identifier>
    <location>
        <url>https://aclanthology.org/2014.iwslt-papers.6</url>
    </location>
    <part>
        <date>2014-dec 4-5</date>
        <extent unit="page">
            <start>192</start>
            <end>199</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Discriminative adaptation of continuous space translation models
%A Do, Quoc-Khanh
%A Allauzen, Alexandre
%A Yvon, François
%Y Federico, Marcello
%Y Stüker, Sebastian
%Y Yvon, François
%S Proceedings of the 11th International Workshop on Spoken Language Translation: Papers
%D 2014
%8 dec 4 5
%C Lake Tahoe, California
%F do-etal-2014-discriminative
%X In this paper we explore various adaptation techniques for continuous space translation models (CSTMs). We consider the following practical situation: given a large scale, state-of-the-art SMT system containing a CSTM, the task is to adapt the CSTM to a new domain using a (relatively) small in-domain parallel corpus. Our method relies on the definition of a new discriminative loss function for the CSTM that borrows from both the max-margin and pair-wise ranking approaches. In our experiments, the baseline out-of-domain SMT system is initially trained for the WMT News translation task, and the CSTM is to be adapted to the lecture translation task as defined by IWSLT evaluation campaign. Experimental results show that an improvement of 1.5 BLEU points can be achieved with the proposed adaptation method.
%U https://aclanthology.org/2014.iwslt-papers.6
%P 192-199

Markdown (Informal)

[Discriminative adaptation of continuous space translation models](https://aclanthology.org/2014.iwslt-papers.6) (Do et al., IWSLT 2014)

• Discriminative adaptation of continuous space translation models (Do et al., IWSLT 2014)

ACL

• Quoc-Khanh Do, Alexandre Allauzen, and François Yvon. 2014. Discriminative adaptation of continuous space translation models. In Proceedings of the 11th International Workshop on Spoken Language Translation: Papers, pages 192–199, Lake Tahoe, California.