<?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-03690174</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="2026-05-03T15:56:07+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection</title>
            <author role="aut">
              <persName>
                <forename type="first">Tulika</forename>
                <surname>Bose</surname>
              </persName>
              <email type="md5">2638d81689cdbde10bc6167af7d35c59</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="numeric">1096690</idno>
              <idno type="halauthorid" notation="string">1284119-1096690</idno>
              <affiliation ref="#struct-420403"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nikolaos</forename>
                <surname>Aletras</surname>
              </persName>
              <email type="md5">b0261c4ed2621a21866eaa278ab1ba01</email>
              <email type="domain">sheffield.ac.uk</email>
              <idno type="idhal" notation="numeric">1136302</idno>
              <idno type="halauthorid" notation="string">2519390-1136302</idno>
              <affiliation ref="#struct-153591"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Irina</forename>
                <surname>Illina</surname>
              </persName>
              <email type="md5">ce064b30f59430508fd3dc2337083dd1</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">irina-illina</idno>
              <idno type="idhal" notation="numeric">15663</idno>
              <idno type="halauthorid" notation="string">839-15663</idno>
              <idno type="IDREF">https://www.idref.fr/120731746</idno>
              <affiliation ref="#struct-420403"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Dominique</forename>
                <surname>Fohr</surname>
              </persName>
              <email type="md5">8e5e638ec2a51d07ccd00424312223ce</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">dominique-fohr</idno>
              <idno type="idhal" notation="numeric">15652</idno>
              <idno type="halauthorid" notation="string">3052-15652</idno>
              <idno type="IDREF">https://www.idref.fr/031092942</idno>
              <orgName ref="#struct-441569"/>
              <affiliation ref="#struct-420403"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Tulika</forename>
                <surname>Bose</surname>
              </persName>
              <email type="md5">2638d81689cdbde10bc6167af7d35c59</email>
              <email type="domain">loria.fr</email>
            </editor>
            <funder ref="#projanr-42100"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-06-07 23:44:14</date>
              <date type="whenModified">2025-11-04 12:02:35</date>
              <date type="whenReleased">2022-06-08 13:30:47</date>
              <date type="whenProduced">2022-05-22</date>
              <date type="whenEndEmbargoed">2022-06-07</date>
              <ref type="file" target="https://inria.hal.science/hal-03690174v1/document">
                <date notBefore="2022-06-07"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-03690174v1/file/ACL2022_Dyn_Ref_Tulika_Tracking-5.pdf" id="file-3690174-3222679">
                <date notBefore="2022-06-07"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1025043">
                <persName>
                  <forename>Tulika</forename>
                  <surname>Bose</surname>
                </persName>
                <email type="md5">2638d81689cdbde10bc6167af7d35c59</email>
                <email type="domain">loria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03690174</idno>
            <idno type="halUri">https://inria.hal.science/hal-03690174</idno>
            <idno type="halBibtex">bose:hal-03690174</idno>
            <idno type="halRefHtml">&lt;i&gt;ACL 2022 - 60th meeting Association for Computational Linguistics Findings&lt;/i&gt;, May 2022, Dublin, Ireland. &lt;a target="_blank" href="https://dx.doi.org/10.18653/v1/2022.findings-acl.32"&gt;&amp;#x27E8;10.18653/v1/2022.findings-acl.32&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">ACL 2022 - 60th meeting Association for Computational Linguistics Findings, May 2022, Dublin, Ireland. &amp;#x27E8;10.18653/v1/2022.findings-acl.32&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3690174-3222679"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="LORIA2">Publications du LORIA</idno>
            <idno type="stamp" n="INRIA-NANCY-GRAND-EST">INRIA Nancy - Grand Est</idno>
            <idno type="stamp" n="GRID5000">Grid'5000</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="CENTRALESUPELEC">Ecole CentraleSupélec</idno>
            <idno type="stamp" n="UNIV-LORRAINE">Université de Lorraine</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="LORIA">Laboratoire Lorrain de Recherche en Informatique et ses Applications</idno>
            <idno type="stamp" n="LORIA-NLPKD" corresp="LORIA">Department of Natural Language Processing &amp; Knowledge Discovery</idno>
            <idno type="stamp" n="LUE-UL">LUE Lorraine Université d'Excellence</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="INRIA-ROYAUMEUNI">INRIA-ROYAUMEUNI</idno>
            <idno type="stamp" n="SLICES-FR">Publications from users of the SILECS research infrastructure</idno>
            <idno type="stamp" n="AM2I-UL">Pôle scientifique Automatique, Mathématiques, Informatique et leurs Intéractions de l'Université de Lorraine</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">Dynamically Refined Regularization for Improving Cross-corpora Hate Speech Detection</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Tulika</forename>
                    <surname>Bose</surname>
                  </persName>
                  <email type="md5">2638d81689cdbde10bc6167af7d35c59</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="numeric">1096690</idno>
                  <idno type="halauthorid" notation="string">1284119-1096690</idno>
                  <affiliation ref="#struct-420403"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nikolaos</forename>
                    <surname>Aletras</surname>
                  </persName>
                  <email type="md5">b0261c4ed2621a21866eaa278ab1ba01</email>
                  <email type="domain">sheffield.ac.uk</email>
                  <idno type="idhal" notation="numeric">1136302</idno>
                  <idno type="halauthorid" notation="string">2519390-1136302</idno>
                  <affiliation ref="#struct-153591"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Irina</forename>
                    <surname>Illina</surname>
                  </persName>
                  <email type="md5">ce064b30f59430508fd3dc2337083dd1</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">irina-illina</idno>
                  <idno type="idhal" notation="numeric">15663</idno>
                  <idno type="halauthorid" notation="string">839-15663</idno>
                  <idno type="IDREF">https://www.idref.fr/120731746</idno>
                  <affiliation ref="#struct-420403"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Dominique</forename>
                    <surname>Fohr</surname>
                  </persName>
                  <email type="md5">8e5e638ec2a51d07ccd00424312223ce</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">dominique-fohr</idno>
                  <idno type="idhal" notation="numeric">15652</idno>
                  <idno type="halauthorid" notation="string">3052-15652</idno>
                  <idno type="IDREF">https://www.idref.fr/031092942</idno>
                  <orgName ref="#struct-441569"/>
                  <affiliation ref="#struct-420403"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>ACL 2022 - 60th meeting Association for Computational Linguistics Findings</title>
                  <date type="start">2022-05-22</date>
                  <date type="end">2022-05-27</date>
                  <settlement>Dublin</settlement>
                  <country key="IE">Ireland</country>
                </meeting>
                <imprint/>
              </monogr>
              <idno type="doi">10.18653/v1/2022.findings-acl.32</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="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>Hate speech classifiers exhibit substantial performance degradation when evaluated on datasets different from the source. This is due to learning spurious correlations between words that are not necessarily relevant to hateful language, and hate speech labels from the training corpus. Previous work has attempted to mitigate this problem by regularizing specific terms from pre-defined static dictionaries. While this has been demonstrated to improve the generalizability of classifiers, the coverage of such methods is limited and the dictionaries require regular manual updates from human experts. In this paper, we propose to automatically identify and reduce spurious correlations using attribution methods with dynamic refinement of the list of terms that need to be regularized during training. Our approach is flexible and improves the cross-corpora performance over previous work independently and in combination with pre-defined dictionaries.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-420403" status="VALID">
          <idno type="RNSR">201421147E</idno>
          <idno type="ROR">https://ror.org/02mv3qy73</idno>
          <orgName>Speech Modeling for Facilitating Oral-Based Communication</orgName>
          <orgName type="acronym">MULTISPEECH</orgName>
          <date type="start">2015-07-01</date>
          <date type="end">2029-04-30</date>
          <desc>
            <address>
              <addrLine>Centre Inria de l'Université de Lorraine , 615 Rue du Jardin-Botanique, 54600 Villers-lès-Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/multispeech</ref>
          </desc>
          <listRelation>
            <relation active="#struct-129671" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-423086" type="direct"/>
            <relation active="#struct-206040" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-153591" status="VALID">
          <idno type="ROR">https://ror.org/05krs5044</idno>
          <orgName>University of Sheffield [Sheffield]</orgName>
          <desc>
            <address>
              <addrLine>Western Bank Sheffield S10 2TN</addrLine>
              <country key="GB"/>
            </address>
            <ref type="url">http://www.sheffield.ac.uk/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-129671" status="VALID">
          <idno type="RNSR">198618246Y</idno>
          <idno type="ROR">https://ror.org/03fcjvn64</idno>
          <orgName>Centre Inria de l'Université de Lorraine</orgName>
          <desc>
            <address>
              <addrLine>615 rue du Jardin Botanique 54600 Villers-lès-Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/nancy</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>
        <org type="department" xml:id="struct-423086" status="VALID">
          <orgName>Department of Natural Language Processing &amp; Knowledge Discovery</orgName>
          <orgName type="acronym">LORIA - NLPKD</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr/en/research/departments/natural-language-processing-and-knowledge-discovery/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-206040" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-411575" type="indirect"/>
            <relation active="#struct-413289" type="indirect"/>
            <relation name="UMR7503" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-206040" status="VALID">
          <idno type="IdRef">067077927</idno>
          <idno type="ISNI">0000000121795429</idno>
          <idno type="RNSR">198912571S</idno>
          <idno type="IdUnivLorraine">[UL]RSI--</idno>
          <idno type="ROR">https://ror.org/02vnf0c38</idno>
          <orgName>Laboratoire Lorrain de Recherche en Informatique et ses Applications</orgName>
          <orgName type="acronym">LORIA</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Scientifique BP 239 54506 Vandoeuvre-lès-Nancy Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.loria.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-411575" type="direct"/>
            <relation active="#struct-413289" type="direct"/>
            <relation name="UMR7503" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-411575" status="VALID">
          <idno type="IdRef">184443237</idno>
          <idno type="ROR">https://ror.org/019tcpt25</idno>
          <orgName>CentraleSupélec</orgName>
          <desc>
            <address>
              <addrLine>3, rue Joliot Curie,Plateau de Moulon,91192 GIF-SUR-YVETTE Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.centralesupelec.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-413289" status="VALID">
          <idno type="IdRef">157040569</idno>
          <idno type="IdUnivLorraine">[UL]100--</idno>
          <idno type="ROR">https://ror.org/04vfs2w97</idno>
          <orgName>Université de Lorraine</orgName>
          <orgName type="acronym">UL</orgName>
          <date type="start">2012-01-01</date>
          <desc>
            <address>
              <addrLine>34 cours Léopold - CS 25233 - 54052 Nancy cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lorraine.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-42100" status="VALID">
          <idno type="anr">ANR-15-IDEX-0004</idno>
          <idno type="program">ISITE</idno>
          <orgName>LUE</orgName>
          <desc>Isite LUE</desc>
          <date type="start">2015</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>