<?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-04173454</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="2026-05-16T20:49:03+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Domain-Specific Word Embeddings with Structure Prediction</title>
            <author role="aut">
              <persName>
                <forename type="first">David</forename>
                <surname>Lassner</surname>
              </persName>
              <idno type="halauthorid">1809095-0</idno>
              <affiliation ref="#struct-86624"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Stephanie</forename>
                <surname>Brandl</surname>
              </persName>
              <idno type="halauthorid">1978174-0</idno>
              <affiliation ref="#struct-86624"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Anne</forename>
                <surname>Baillot</surname>
              </persName>
              <email type="md5">e81d4b35751d2e3f110a9b12fed0fbf7</email>
              <email type="domain">univ-lemans.fr</email>
              <idno type="idhal" notation="string">annebaillot</idno>
              <idno type="idhal" notation="numeric">3610</idno>
              <idno type="halauthorid" notation="string">24997-3610</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4593-059X</idno>
              <idno type="VIAF">https://viaf.org/viaf/39592455</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=YbT-S-EAAAAJ&amp;hl=en&amp;oi=ao</idno>
              <idno type="IDREF">https://www.idref.fr/073633828</idno>
              <affiliation ref="#struct-182700"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Shinichi</forename>
                <surname>Nakajima</surname>
              </persName>
              <idno type="halauthorid">1809098-0</idno>
              <affiliation ref="#struct-86624"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Anne</forename>
                <surname>Baillot</surname>
              </persName>
              <email type="md5">30792badbd7ee1c5bb02c8ee17a5d9bf</email>
              <email type="domain">dariah.eu</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-07-29 09:43:42</date>
              <date type="whenModified">2024-05-24 19:48:04</date>
              <date type="whenReleased">2023-07-29 09:43:43</date>
              <date type="whenProduced">2023</date>
              <ref type="externalLink" target="http://arxiv.org/pdf/2210.04962"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="170671">
                <persName>
                  <forename>Anne</forename>
                  <surname>Baillot</surname>
                </persName>
                <email type="md5">30792badbd7ee1c5bb02c8ee17a5d9bf</email>
                <email type="domain">dariah.eu</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04173454</idno>
            <idno type="halUri">https://hal.science/hal-04173454</idno>
            <idno type="halBibtex">lassner:hal-04173454</idno>
            <idno type="halRefHtml">&lt;i&gt;Transactions of the Association for Computational Linguistics&lt;/i&gt;, 2023, 11, pp.320-335. &lt;a target="_blank" href="https://dx.doi.org/10.1162/tacl_a_00538"&gt;&amp;#x27E8;10.1162/tacl_a_00538&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Transactions of the Association for Computational Linguistics, 2023, 11, pp.320-335. &amp;#x27E8;10.1162/tacl_a_00538&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-ANGERS">Université d'Angers</idno>
            <idno type="stamp" n="UNIV-LEMANS">Université du Mans</idno>
            <idno type="stamp" n="3LAM" corresp="UNIV-LEMANS">Langues, Littératures, Linguistique</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Domain-Specific Word Embeddings with Structure Prediction</title>
                <author role="aut">
                  <persName>
                    <forename type="first">David</forename>
                    <surname>Lassner</surname>
                  </persName>
                  <idno type="halauthorid">1809095-0</idno>
                  <affiliation ref="#struct-86624"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Stephanie</forename>
                    <surname>Brandl</surname>
                  </persName>
                  <idno type="halauthorid">1978174-0</idno>
                  <affiliation ref="#struct-86624"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Anne</forename>
                    <surname>Baillot</surname>
                  </persName>
                  <email type="md5">e81d4b35751d2e3f110a9b12fed0fbf7</email>
                  <email type="domain">univ-lemans.fr</email>
                  <idno type="idhal" notation="string">annebaillot</idno>
                  <idno type="idhal" notation="numeric">3610</idno>
                  <idno type="halauthorid" notation="string">24997-3610</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4593-059X</idno>
                  <idno type="VIAF">https://viaf.org/viaf/39592455</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=YbT-S-EAAAAJ&amp;hl=en&amp;oi=ao</idno>
                  <idno type="IDREF">https://www.idref.fr/073633828</idno>
                  <affiliation ref="#struct-182700"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Shinichi</forename>
                    <surname>Nakajima</surname>
                  </persName>
                  <idno type="halauthorid">1809098-0</idno>
                  <affiliation ref="#struct-86624"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">104602</idno>
                <idno type="eissn">2307-387X</idno>
                <title level="j">Transactions of the Association for Computational Linguistics</title>
                <imprint>
                  <publisher>The MIT Press</publisher>
                  <biblScope unit="volume">11</biblScope>
                  <biblScope unit="pp">320-335</biblScope>
                  <date type="datePub">2023</date>
                  <date type="dateEpub">2023</date>
                </imprint>
              </monogr>
              <idno type="arxiv">2210.04962</idno>
              <idno type="doi">10.1162/tacl_a_00538</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Complementary to finding good general word embeddings, an important question for representation learning is to find dynamic word embeddings, for example, across time or domain. Current methods do not offer a way to use or predict information on structure between sub-corpora, time or domain and dynamic embeddings can only be compared after post-alignment. We propose novel word embedding methods that provide general word representations for the whole corpus, domain- specific representations for each sub-corpus, sub-corpus structure, and embedding alignment simultaneously. We present an empirical evaluation on New York Times articles and two English Wikipedia datasets with articles on science and philosophy. Our method, called Word2Vec with Structure Prediction (W2VPred), provides better performance than baselines in terms of the general analogy tests, domain-specific analogy tests, and multiple specific word embedding evaluations as well as structure prediction performance when no structure is given a priori. As a use case in the field of Digital Humanities we demonstrate how to raise novel research questions for high literature from the German Text Archive.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-86624" status="VALID">
          <idno type="ROR">https://ror.org/03v4gjf40</idno>
          <orgName>Technical University of Berlin / Technische Universität Berlin</orgName>
          <orgName type="acronym">TUB</orgName>
          <date type="start">1946-01-01</date>
          <desc>
            <address>
              <addrLine>Straße des 17. Juni 135 10623 Berlin</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.tu.berlin/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-182700" status="VALID">
          <idno type="IdRef">148928641</idno>
          <idno type="ISNI">0000 0001 2291 6181</idno>
          <idno type="RNSR">200815564M</idno>
          <idno type="ROR">https://ror.org/03hq2nj16</idno>
          <idno type="Wikidata">Q51784243</idno>
          <orgName>Langues, Littératures, Linguistique des Universités d'Angers et du Mans</orgName>
          <orgName type="acronym">3L.AM</orgName>
          <date type="start">2008-01-01</date>
          <desc>
            <address>
              <addrLine>Le Mans Université, 3L.AM - UFR de Lettres, Langues et Sciences Humaines, MSH, Avenue Olivier Messiaen - 72085 Le Mans CEDEX 09Université d'Angers, 3L.AM - Faculté de Lettres, Langues et Sciences Humaines, Maison de la Recherche Germaine Tillion, 5 Bis Boulevard Lavoisier - 49045 Angers CEDEX 01</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://3lam.univ-lemans.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-7566" type="direct"/>
            <relation active="#struct-74911" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-7566" status="VALID">
          <idno type="ROR">https://ror.org/01mtcc283</idno>
          <orgName>Le Mans Université</orgName>
          <orgName type="acronym">UM</orgName>
          <desc>
            <address>
              <addrLine>Avenue Olivier Messiaen - 72085 Le Mans cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lemans.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-74911" status="VALID">
          <idno type="IdRef">026402920</idno>
          <idno type="ISNI">0000000122483363</idno>
          <idno type="ROR">https://ror.org/04yrqp957</idno>
          <orgName>Université d'Angers</orgName>
          <orgName type="acronym">UA</orgName>
          <date type="start">1971-10-25</date>
          <desc>
            <address>
              <addrLine>Université d'Angers - 40 Rue de Rennes, BP 73532 - 49035 Angers CEDEX 01</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-angers.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>