<?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-03161637</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="2026-05-15T00:19:26+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora</title>
            <author role="aut">
              <persName>
                <forename type="first">Hila</forename>
                <surname>Gonen</surname>
              </persName>
              <idno type="halauthorid">2165571-0</idno>
              <affiliation ref="#struct-494222"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ganesh</forename>
                <surname>Jawahar</surname>
              </persName>
              <email type="md5">20ca0523fa980da7063a0b83e20ef7b2</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">1092776</idno>
              <idno type="halauthorid" notation="string">1481854-1092776</idno>
              <affiliation ref="#struct-482775"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Djamé</forename>
                <surname>Seddah</surname>
              </persName>
              <email type="md5">1a46dccff44eefe8ac69598e3b186e83</email>
              <email type="domain">paris-sorbonne.fr</email>
              <idno type="idhal" notation="string">djameseddah</idno>
              <idno type="idhal" notation="numeric">11545</idno>
              <idno type="halauthorid" notation="string">1878-11545</idno>
              <idno type="IDREF">https://www.idref.fr/086185136</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0194-8197</idno>
              <affiliation ref="#struct-482775"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Yoav</forename>
                <surname>Goldberg</surname>
              </persName>
              <email type="md5">a8622e2a189a13c7b5a99177c3a87c37</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="numeric">1092777</idno>
              <idno type="halauthorid" notation="string">497129-1092777</idno>
              <affiliation ref="#struct-494222"/>
              <affiliation ref="#struct-476519"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Djamé</forename>
                <surname>Seddah</surname>
              </persName>
              <email type="md5">1a46dccff44eefe8ac69598e3b186e83</email>
              <email type="domain">paris-sorbonne.fr</email>
            </editor>
            <funder ref="#projanr-45801"/>
            <funder ref="#projanr-44644"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-03-07 19:12:11</date>
              <date type="whenModified">2025-09-12 17:04:02</date>
              <date type="whenReleased">2021-03-08 09:13:22</date>
              <date type="whenProduced">2020-07-05</date>
              <date type="whenEndEmbargoed">2021-03-07</date>
              <ref type="file" target="https://inria.hal.science/hal-03161637v1/document">
                <date notBefore="2021-03-07"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-03161637v1/file/2020.acl-main.51.pdf" id="file-3161637-2771890">
                <date notBefore="2021-03-07"/>
              </ref>
              <ref type="externalLink" target="https://www.aclweb.org/anthology/2020.acl-main.51.pdf"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="133971">
                <persName>
                  <forename>Djamé</forename>
                  <surname>Seddah</surname>
                </persName>
                <email type="md5">1a46dccff44eefe8ac69598e3b186e83</email>
                <email type="domain">paris-sorbonne.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03161637</idno>
            <idno type="halUri">https://inria.hal.science/hal-03161637</idno>
            <idno type="halBibtex">gonen:hal-03161637</idno>
            <idno type="halRefHtml">&lt;i&gt;ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics&lt;/i&gt;, Jul 2020, Seattle / Virtual, United States. pp.538-555, &lt;a target="_blank" href="https://dx.doi.org/10.18653/v1/2020.acl-main.51"&gt;&amp;#x27E8;10.18653/v1/2020.acl-main.51&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Jul 2020, Seattle / Virtual, United States. pp.538-555, &amp;#x27E8;10.18653/v1/2020.acl-main.51&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3161637-2771890"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-ROCQ">INRIA Paris - Rocquencourt</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="INRIA-ISRAEL">COPUBLICATION INRIA ISRAEL</idno>
            <idno type="stamp" n="INRIA-ETATSUNIS">Copublications Inria-Etats-Unis</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">Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Hila</forename>
                    <surname>Gonen</surname>
                  </persName>
                  <idno type="halauthorid">2165571-0</idno>
                  <affiliation ref="#struct-494222"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ganesh</forename>
                    <surname>Jawahar</surname>
                  </persName>
                  <email type="md5">20ca0523fa980da7063a0b83e20ef7b2</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">1092776</idno>
                  <idno type="halauthorid" notation="string">1481854-1092776</idno>
                  <affiliation ref="#struct-482775"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Djamé</forename>
                    <surname>Seddah</surname>
                  </persName>
                  <email type="md5">1a46dccff44eefe8ac69598e3b186e83</email>
                  <email type="domain">paris-sorbonne.fr</email>
                  <idno type="idhal" notation="string">djameseddah</idno>
                  <idno type="idhal" notation="numeric">11545</idno>
                  <idno type="halauthorid" notation="string">1878-11545</idno>
                  <idno type="IDREF">https://www.idref.fr/086185136</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0194-8197</idno>
                  <affiliation ref="#struct-482775"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Yoav</forename>
                    <surname>Goldberg</surname>
                  </persName>
                  <email type="md5">a8622e2a189a13c7b5a99177c3a87c37</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="numeric">1092777</idno>
                  <idno type="halauthorid" notation="string">497129-1092777</idno>
                  <affiliation ref="#struct-494222"/>
                  <affiliation ref="#struct-476519"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>ACL 2020 -  58th Annual Meeting of the Association for Computational Linguistics</title>
                  <date type="start">2020-07-05</date>
                  <date type="end">2020-07-10</date>
                  <settlement>Seattle / Virtual</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint>
                  <publisher>Association for Computational Linguistics</publisher>
                  <biblScope unit="pp">538-555</biblScope>
                </imprint>
              </monogr>
              <idno type="doi">10.18653/v1/2020.acl-main.51</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <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>The problem of comparing two bodies of text and searching for words that differ in their usage between them arises often in digital humanities and computational social science. This is commonly approached by training word embeddings on each corpus, aligning the vector spaces, and looking for words whose cosine distance in the aligned space is large. However, these methods often require extensive filtering of the vocabulary to perform well, and-as we show in this work-result in unstable, and hence less reliable, results. We propose an alternative approach that does not use vector space alignment, and instead considers the neighbors of each word. The method is simple, interpretable and stable. We demonstrate its effectiveness in 9 different setups, considering different corpus splitting criteria (age, gender and profession of tweet authors, time of tweet) and different languages (English, French and Hebrew).</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="department" xml:id="struct-494222" status="VALID">
          <orgName>Department of Computer Science at Bar Ilan University</orgName>
          <date type="start">2017-05-04</date>
          <desc>
            <address>
              <addrLine>Faculty of Exact SciencesBar-Ilan University Ramat-Gan5290002 Israel</addrLine>
              <country key="IL"/>
            </address>
            <ref type="url">http://cs.biu.ac.il//en</ref>
          </desc>
          <listRelation>
            <relation active="#struct-303955" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-482775" status="VALID">
          <idno type="RNSR">201722248N</idno>
          <idno type="ROR">https://ror.org/05rnwy495</idno>
          <orgName>Automatic Language Modelling and ANAlysis &amp; Computational Humanities</orgName>
          <orgName type="acronym">ALMAnaCH</orgName>
          <date type="start">2017-01-01</date>
          <date type="end">2029-04-30</date>
          <desc>
            <address>
              <addrLine>48 Rue Barrault, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inria.fr/equipes/almanach</ref>
          </desc>
          <listRelation>
            <relation active="#struct-454310" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-476519" status="VALID">
          <orgName>Allen Institute for Artificial Intelligence</orgName>
          <orgName type="acronym">AI2</orgName>
          <desc>
            <address>
              <country key="US"/>
            </address>
            <ref type="url">http://allenai.org/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-303955" status="VALID">
          <idno type="ROR">https://ror.org/03kgsv495</idno>
          <orgName>Bar-Ilan University [Israël]</orgName>
          <desc>
            <address>
              <addrLine>Ramat-Gan 5290002,Israel</addrLine>
              <country key="IL"/>
            </address>
            <ref type="url">http://www1.biu.ac.il/indexE.php</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-454310" status="VALID">
          <idno type="IdRef">241614864</idno>
          <idno type="RNSR">196718247G</idno>
          <idno type="ROR">https://ror.org/05eyd5d35</idno>
          <orgName>Centre Inria de Paris</orgName>
          <date type="start">2016-03-10</date>
          <desc>
            <address>
              <addrLine>48 Rue Barrault, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/paris</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-45801" status="VALID">
          <idno type="anr">ANR-15-CE38-0011</idno>
          <orgName>SoSweet</orgName>
          <desc>Une sociolinguistique de Twitter : liens sociaux et variations linguistiques</desc>
          <date type="start">2015</date>
        </org>
        <org type="anrProject" xml:id="projanr-44644" status="VALID">
          <idno type="anr">ANR-16-CE33-0021</idno>
          <orgName>PARSITI</orgName>
          <desc>Analyser l'impossible, Traduire l'improbable</desc>
          <date type="start">2016</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>