<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-01157888</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-20T13:52:36+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Comparison of Data Selection Techniques for the Translation of Video Lectures</title>
            <author role="aut">
              <persName>
                <forename type="first">Joern</forename>
                <surname>Wuebker</surname>
              </persName>
              <email type="md5">e4796ea9263dc2c9199fee4ccd49ceea</email>
              <email type="domain">cs.rwth-aachen.de</email>
              <idno type="idhal" notation="numeric">966731</idno>
              <idno type="halauthorid" notation="string">915323-966731</idno>
              <affiliation ref="#struct-109169"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hermann</forename>
                <surname>Ney</surname>
              </persName>
              <email type="md5">59de51367caeb9af5576cca3876fd832</email>
              <email type="domain">cs.rwth-aachen.de</email>
              <idno type="idhal" notation="numeric">932087</idno>
              <idno type="halauthorid" notation="string">475981-932087</idno>
              <idno type="IDREF">https://www.idref.fr/15580524X</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7694-8370</idno>
              <affiliation ref="#struct-109169"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Martínez-Villaronga</forename>
                <surname>Adrià</surname>
              </persName>
              <email type="md5">6b48dbedd0d3e3444bb1a9841b3e86c0</email>
              <email type="domain">dsic.upv.es</email>
              <idno type="idhal" notation="numeric">966732</idno>
              <idno type="halauthorid" notation="string">915324-966732</idno>
              <affiliation ref="#struct-300772"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Adrià</forename>
                <surname>Giménez</surname>
              </persName>
              <email type="md5">a496e9f078eff5b829cc8b1e451203db</email>
              <email type="domain">dsic.upv.es</email>
              <idno type="idhal" notation="numeric">966733</idno>
              <idno type="halauthorid" notation="string">915325-966733</idno>
              <affiliation ref="#struct-300772"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Alfons</forename>
                <surname>Juan</surname>
              </persName>
              <email type="md5">cb3749a1d89a9e29d58aa108cbfb8423</email>
              <email type="domain">dsic.upv.es</email>
              <idno type="idhal" notation="numeric">966734</idno>
              <idno type="halauthorid" notation="string">915326-966734</idno>
              <affiliation ref="#struct-300772"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Christophe</forename>
                <surname>Servan</surname>
              </persName>
              <email type="md5">65a2a8d7160b6e43a6e9caa24d9af1f2</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">servan</idno>
              <idno type="idhal" notation="numeric">4128</idno>
              <idno type="halauthorid" notation="string">9504-4128</idno>
              <idno type="IDREF">https://www.idref.fr/147053609</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-2306-7075</idno>
              <affiliation ref="#struct-23641"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marc</forename>
                <surname>Dymetman</surname>
              </persName>
              <email type="md5">68ab77519fc81af2db3fd2fad65d6468</email>
              <email type="domain">xrce.xerox.com</email>
              <idno type="idhal" notation="numeric">966735</idno>
              <idno type="halauthorid" notation="string">168190-966735</idno>
              <affiliation ref="#struct-23641"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Shachar</forename>
                <surname>Mirkin</surname>
              </persName>
              <email type="md5">06b1fd7237992231c054dfa891a63f20</email>
              <email type="domain">xrce.xerox.com</email>
              <idno type="idhal" notation="numeric">966736</idno>
              <idno type="halauthorid" notation="string">807045-966736</idno>
              <affiliation ref="#struct-23641"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Christophe</forename>
                <surname>Servan</surname>
              </persName>
              <email type="md5">65a2a8d7160b6e43a6e9caa24d9af1f2</email>
              <email type="domain">gmail.com</email>
            </editor>
            <funder ref="#projeurop-89620"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2015-05-28 17:44:50</date>
              <date type="whenModified">2024-12-03 13:00:08</date>
              <date type="whenReleased">2015-05-29 08:50:16</date>
              <date type="whenProduced">2014-10-22</date>
              <date type="whenEndEmbargoed">2015-05-28</date>
              <ref type="file" target="https://hal.science/hal-01157888v1/document">
                <date notBefore="2015-05-28"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01157888v1/file/paperAMTA.pdf" id="file-1157888-1240686">
                <date notBefore="2015-05-28"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="164580">
                <persName>
                  <forename>Christophe</forename>
                  <surname>Servan</surname>
                </persName>
                <email type="md5">65a2a8d7160b6e43a6e9caa24d9af1f2</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01157888</idno>
            <idno type="halUri">https://hal.science/hal-01157888</idno>
            <idno type="halBibtex">wuebker:hal-01157888</idno>
            <idno type="halRefHtml">&lt;i&gt;The eleventh biennial conference of the Association for Machine Translation in the Americas (AMTA-2014)&lt;/i&gt;, AMTA, Oct 2014, Vancouver, Canada</idno>
            <idno type="halRef">The eleventh biennial conference of the Association for Machine Translation in the Americas (AMTA-2014), AMTA, Oct 2014, Vancouver, Canada</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1157888-1240686"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="OPENAIRE">OpenAIRE</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Comparison of Data Selection Techniques for the Translation of Video Lectures</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Joern</forename>
                    <surname>Wuebker</surname>
                  </persName>
                  <email type="md5">e4796ea9263dc2c9199fee4ccd49ceea</email>
                  <email type="domain">cs.rwth-aachen.de</email>
                  <idno type="idhal" notation="numeric">966731</idno>
                  <idno type="halauthorid" notation="string">915323-966731</idno>
                  <affiliation ref="#struct-109169"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hermann</forename>
                    <surname>Ney</surname>
                  </persName>
                  <email type="md5">59de51367caeb9af5576cca3876fd832</email>
                  <email type="domain">cs.rwth-aachen.de</email>
                  <idno type="idhal" notation="numeric">932087</idno>
                  <idno type="halauthorid" notation="string">475981-932087</idno>
                  <idno type="IDREF">https://www.idref.fr/15580524X</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7694-8370</idno>
                  <affiliation ref="#struct-109169"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Martínez-Villaronga</forename>
                    <surname>Adrià</surname>
                  </persName>
                  <email type="md5">6b48dbedd0d3e3444bb1a9841b3e86c0</email>
                  <email type="domain">dsic.upv.es</email>
                  <idno type="idhal" notation="numeric">966732</idno>
                  <idno type="halauthorid" notation="string">915324-966732</idno>
                  <affiliation ref="#struct-300772"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Adrià</forename>
                    <surname>Giménez</surname>
                  </persName>
                  <email type="md5">a496e9f078eff5b829cc8b1e451203db</email>
                  <email type="domain">dsic.upv.es</email>
                  <idno type="idhal" notation="numeric">966733</idno>
                  <idno type="halauthorid" notation="string">915325-966733</idno>
                  <affiliation ref="#struct-300772"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Alfons</forename>
                    <surname>Juan</surname>
                  </persName>
                  <email type="md5">cb3749a1d89a9e29d58aa108cbfb8423</email>
                  <email type="domain">dsic.upv.es</email>
                  <idno type="idhal" notation="numeric">966734</idno>
                  <idno type="halauthorid" notation="string">915326-966734</idno>
                  <affiliation ref="#struct-300772"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Christophe</forename>
                    <surname>Servan</surname>
                  </persName>
                  <email type="md5">65a2a8d7160b6e43a6e9caa24d9af1f2</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">servan</idno>
                  <idno type="idhal" notation="numeric">4128</idno>
                  <idno type="halauthorid" notation="string">9504-4128</idno>
                  <idno type="IDREF">https://www.idref.fr/147053609</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-2306-7075</idno>
                  <affiliation ref="#struct-23641"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marc</forename>
                    <surname>Dymetman</surname>
                  </persName>
                  <email type="md5">68ab77519fc81af2db3fd2fad65d6468</email>
                  <email type="domain">xrce.xerox.com</email>
                  <idno type="idhal" notation="numeric">966735</idno>
                  <idno type="halauthorid" notation="string">168190-966735</idno>
                  <affiliation ref="#struct-23641"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Shachar</forename>
                    <surname>Mirkin</surname>
                  </persName>
                  <email type="md5">06b1fd7237992231c054dfa891a63f20</email>
                  <email type="domain">xrce.xerox.com</email>
                  <idno type="idhal" notation="numeric">966736</idno>
                  <idno type="halauthorid" notation="string">807045-966736</idno>
                  <affiliation ref="#struct-23641"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>The eleventh biennial conference of the Association for Machine Translation in the Americas (AMTA-2014)</title>
                  <date type="start">2014-10-22</date>
                  <date type="end">2014-10-26</date>
                  <settlement>Vancouver</settlement>
                  <country key="CA">Canada</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>AMTA</name>
                </respStmt>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Speech translation</term>
                <term xml:lang="en">Domain Adaptation</term>
                <term xml:lang="en">Statistical machine translation</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>For the task of online translation of scientific video lectures, using huge models is not possible. In order to get smaller and efficient models, we perform data selection. In this paper, we perform a qualitative and quantitative comparison of several data selection techniques, based on cross-entropy and infrequent n-gram criteria. In terms of BLEU, a combination of translation and language model cross-entropy achieves the most stable results. As another important criterion for measuring translation quality in our application, we identify the number of out-of-vocabulary words. Here, infrequent n-gram recovery shows superior performance. Finally, we combine the two selection techniques in order to benefit from both their strengths.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-109169" status="VALID">
          <orgName>Department of Computer Science [Aachen]</orgName>
          <desc>
            <address>
              <addrLine>RWTH Aachen University Department of Computer Science Ahornstr. 55 52074 Aachen</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">http://www.informatik.rwth-aachen.de/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-303510" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300772" status="VALID">
          <idno type="ROR">https://ror.org/01460j859</idno>
          <orgName>Universitat Politècnica de València = Universitad Politecnica de Valencia = Polytechnic University of Valencia</orgName>
          <orgName type="acronym">UPV</orgName>
          <desc>
            <address>
              <addrLine>Camino de Vera, s/n 46022 Valencia</addrLine>
              <country key="ES"/>
            </address>
            <ref type="url">http://www.upv.es/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-23641" status="VALID">
          <orgName>Xerox Research Centre Europe [Meylan]</orgName>
          <desc>
            <address>
              <addrLine>Xerox Research Centre Europe 6 Chemin de Maupertuis 38240 Meylan, FRANCE</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.xrce.xerox.com</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301733" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-303510" status="VALID">
          <idno type="IdRef">074130323</idno>
          <idno type="ISNI">000000010728696X</idno>
          <idno type="ROR">https://ror.org/04xfq0f34</idno>
          <idno type="Wikidata">Q273263</idno>
          <orgName>RWTH Aachen University = Rheinisch-Westfälische Technische Hochschule Aachen</orgName>
          <orgName type="acronym">RWTH Aachen</orgName>
          <date type="start">1870-01-01</date>
          <desc>
            <address>
              <addrLine>RWTH Aachen –  Templergraben 55 – 52062 Aachen (Hausanschrift) – 52056 Aachen (Postanschrift) – Deutschland</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">http://www.rwth-aachen.de/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-301733" status="VALID">
          <orgName>Xerox Company</orgName>
          <desc>
            <address>
              <country key="US"/>
            </address>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="europeanProject" xml:id="projeurop-89620" status="VALID">
          <idno type="number">287755</idno>
          <idno type="program">FP7-ICT-2011-7</idno>
          <idno type="call">FP7-ICT-2011-7</idno>
          <orgName>transLectures</orgName>
          <desc>Transcription and Translation of Video Lectures</desc>
          <date type="start">2011-01-11</date>
          <date type="end">2014-10-31</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>