<?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 ujm-01016381</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="2026-05-16T13:22:09+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Using Proximity and Tag Weights for Focused Retrieval in Structured Documents</title>
            <author role="aut">
              <persName>
                <forename type="first">Michel</forename>
                <surname>Beigbeder</surname>
              </persName>
              <email type="md5">97b42b41aefa476bf3365659fc7f6441</email>
              <email type="domain">emse.fr</email>
              <idno type="idhal" notation="numeric">840581</idno>
              <idno type="halauthorid" notation="string">210957-840581</idno>
              <affiliation ref="#struct-174087"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mathias</forename>
                <surname>Géry</surname>
              </persName>
              <email type="md5">686d37af3c854b72c7c8750ff105a483</email>
              <email type="domain">univ-st-etienne.fr</email>
              <idno type="idhal" notation="numeric">843869</idno>
              <idno type="halauthorid" notation="string">119404-843869</idno>
              <affiliation ref="#struct-17835"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Christine</forename>
                <surname>Largeron</surname>
              </persName>
              <email type="md5">74abe502db975476802cb7b7b409ed60</email>
              <email type="domain">univ-st-etienne.fr</email>
              <idno type="idhal" notation="string">christine-largeron</idno>
              <idno type="idhal" notation="numeric">5702</idno>
              <idno type="halauthorid" notation="string">3566-5702</idno>
              <idno type="IDREF">https://www.idref.fr/029304121</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-1059-4095</idno>
              <affiliation ref="#struct-17835"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Mathias</forename>
                <surname>Géry</surname>
              </persName>
              <email type="md5">686d37af3c854b72c7c8750ff105a483</email>
              <email type="domain">univ-st-etienne.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2014-06-30 10:24:18</date>
              <date type="whenWritten">2013-03-25</date>
              <date type="whenModified">2026-04-23 14:50:04</date>
              <date type="whenReleased">2014-07-01 10:48:58</date>
              <date type="whenProduced">2015-06-18</date>
              <date type="whenEndEmbargoed">2014-06-30</date>
              <ref type="file" target="https://ujm.hal.science/ujm-01016381v1/document">
                <date notBefore="2014-06-30"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://ujm.hal.science/ujm-01016381v1/file/2013_KAIS.pdf" id="file-1016381-814080">
                <date notBefore="2014-06-30"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="131963">
                <persName>
                  <forename>Mathias</forename>
                  <surname>Géry</surname>
                </persName>
                <email type="md5">686d37af3c854b72c7c8750ff105a483</email>
                <email type="domain">univ-st-etienne.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">ujm-01016381</idno>
            <idno type="halUri">https://ujm.hal.science/ujm-01016381</idno>
            <idno type="halBibtex">beigbeder:ujm-01016381</idno>
            <idno type="halRefHtml">&lt;i&gt;Knowledge and Information Systems (KAIS)&lt;/i&gt;, 2015, 44 (1), pp.51-76. &lt;a target="_blank" href="https://dx.doi.org/10.1007/s10115-014-0767-6"&gt;&amp;#x27E8;10.1007/s10115-014-0767-6&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Knowledge and Information Systems (KAIS), 2015, 44 (1), pp.51-76. &amp;#x27E8;10.1007/s10115-014-0767-6&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1016381-814080"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-ST-ETIENNE">Université Jean Monnet - Saint-Etienne</idno>
            <idno type="stamp" n="EMSE" corresp="INSTITUT-MINES-TELECOM">Ecole Nationale Supérieure des Mines de Saint-Etienne</idno>
            <idno type="stamp" n="IOGS" corresp="PARISTECH">Institut d'Optique Graduate School</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="PARISTECH">ParisTech</idno>
            <idno type="stamp" n="FAYOL-ENSMSE" corresp="EMSE">FAYOL - Institut Henri Fayol</idno>
            <idno type="stamp" n="ISCOD-ENSMSE" corresp="EMSE">FAYOL / ISCOD : Informatique pour les Systèmes Coopératifs Ouverts et Décentralisés</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="INSTITUTS-TELECOM">composantes instituts telecom </idno>
            <idno type="stamp" n="LABORATOIRE-HUBERT-CURIEN" corresp="UNIV-ST-ETIENNE">LAboratoire Hubert Curien</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">Using Proximity and Tag Weights for Focused Retrieval in Structured Documents</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Michel</forename>
                    <surname>Beigbeder</surname>
                  </persName>
                  <email type="md5">97b42b41aefa476bf3365659fc7f6441</email>
                  <email type="domain">emse.fr</email>
                  <idno type="idhal" notation="numeric">840581</idno>
                  <idno type="halauthorid" notation="string">210957-840581</idno>
                  <affiliation ref="#struct-174087"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mathias</forename>
                    <surname>Géry</surname>
                  </persName>
                  <email type="md5">686d37af3c854b72c7c8750ff105a483</email>
                  <email type="domain">univ-st-etienne.fr</email>
                  <idno type="idhal" notation="numeric">843869</idno>
                  <idno type="halauthorid" notation="string">119404-843869</idno>
                  <affiliation ref="#struct-17835"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Christine</forename>
                    <surname>Largeron</surname>
                  </persName>
                  <email type="md5">74abe502db975476802cb7b7b409ed60</email>
                  <email type="domain">univ-st-etienne.fr</email>
                  <idno type="idhal" notation="string">christine-largeron</idno>
                  <idno type="idhal" notation="numeric">5702</idno>
                  <idno type="halauthorid" notation="string">3566-5702</idno>
                  <idno type="IDREF">https://www.idref.fr/029304121</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-1059-4095</idno>
                  <affiliation ref="#struct-17835"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">16631</idno>
                <idno type="issn">0219-1377</idno>
                <idno type="eissn">0219-3116</idno>
                <title level="j">Knowledge and Information Systems (KAIS)</title>
                <imprint>
                  <publisher>Springer</publisher>
                  <biblScope unit="volume">44</biblScope>
                  <biblScope unit="issue">1</biblScope>
                  <biblScope unit="pp">51-76</biblScope>
                  <date type="datePub">2015-06-18</date>
                  <date type="dateEpub">2014-05-18</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1007/s10115-014-0767-6</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Tags</term>
                <term xml:lang="en">Focused information retrieval</term>
                <term xml:lang="en">Structured information retrieval</term>
                <term xml:lang="en">Proximity</term>
                <term xml:lang="en">XML</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ir">Computer Science [cs]/Information Retrieval [cs.IR]</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>Focused information retrieval is concerned with the retrieval of small units of information. In this context, the structure of the documents as well as the proximity among query terms have been found useful for improving retrieval effectiveness. In this article, we propose an approach combining the proximity of the terms and the tags which mark these terms. Our approach is based on a Fetch and Browse method where the fetch step is performed with BM25 and the browse step with a structure enhanced proximity model. In this way, the ranking of a document depends not only upon the existence of the query terms within the document but also upon the tags which mark these terms. Thus, the document tends to be highly relevant when query terms are close together and are emphasized by tags. The evaluation of this model on a large XML structured collection provided by the INEX 2010 XML IR evaluation campaign shows that the use of term proximity and structure improves the retrieval effectiveness of BM25 in the context of focused information retrieval.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-174087" status="VALID">
          <orgName>Département Informatique pour les Systèmes Coopératifs Ouverts et Décentralisés</orgName>
          <orgName type="acronym">ISCOD-ENSMSE</orgName>
          <desc>
            <address>
              <addrLine>158 cours Fauriel 42023 Saint-Etienne Cedex 2</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-29212" type="direct"/>
            <relation active="#struct-302102" type="indirect"/>
            <relation active="#struct-344044" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-17835" status="VALID">
          <idno type="IdRef">164609741</idno>
          <idno type="ISNI">0000 0000 9955 0977</idno>
          <idno type="RNSR">199511960B</idno>
          <idno type="ROR">https://ror.org/0028p8r67</idno>
          <orgName>Laboratoire Hubert Curien</orgName>
          <orgName type="acronym">LabHC</orgName>
          <date type="start">2006-01-01</date>
          <desc>
            <address>
              <addrLine>Bâtiment F 18 Rue du Professeur Benoît Lauras42000 Saint-Etienne</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://laboratoirehubertcurien.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300036" type="direct"/>
            <relation active="#struct-300284" type="direct"/>
            <relation active="#struct-1327915" type="indirect"/>
            <relation name="UMR5516" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-29212" status="VALID">
          <orgName>École des Mines de Saint-Étienne</orgName>
          <orgName type="acronym">Mines Saint-Étienne MSE</orgName>
          <desc>
            <address>
              <addrLine>158, Cours Fauriel - 42023 Saint Étienne cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.mines-stetienne.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302102" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-302102" status="VALID">
          <idno type="IdRef">192427156</idno>
          <idno type="ISNI">000000012202567X</idno>
          <idno type="ROR">https://ror.org/025vp2923</idno>
          <idno type="Wikidata">Q27962533</idno>
          <orgName>Institut Mines-Télécom [Paris]</orgName>
          <orgName type="acronym">IMT</orgName>
          <date type="start">2012-03-01</date>
          <desc>
            <address>
              <addrLine>19 Place Marguerite Perey, 91120 Palaiseau</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-344044" status="VALID">
          <orgName>Institut Henri Fayol</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300036" status="VALID">
          <idno type="IdRef">110047702</idno>
          <orgName>Institut d'Optique Graduate School</orgName>
          <orgName type="acronym">IOGS</orgName>
          <desc>
            <address>
              <addrLine>2 avenue Augustin Fresnel, 91127 Palaiseau Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.institutoptique.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300284" status="VALID">
          <idno type="IdRef">028209966</idno>
          <idno type="ISNI">0000 0001 2158 1682</idno>
          <idno type="ROR">https://ror.org/04yznqr36</idno>
          <idno type="Wikidata">Q623154</idno>
          <orgName>Université Jean Monnet - Saint-Étienne</orgName>
          <orgName type="acronym">UJM</orgName>
          <date type="start">1969-03-27</date>
          <date type="end">2025-01-01</date>
          <desc>
            <address>
              <addrLine>10, Rue Tréfilerie – CS 8230142023 Saint-Étienne Cedex 2</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-st-etienne.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1327915" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-1327915" status="VALID">
          <idno type="IdRef">285395831</idno>
          <orgName>Université Jean Monnet (EPSCPE)</orgName>
          <orgName type="acronym">UJM EPE</orgName>
          <date type="start">2025-01-01</date>
          <desc>
            <address>
              <addrLine>10 rue Tréfilerie42100 Saint-Etienne</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.univ-st-etienne.fr/fr/index.html</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>
    </back>
  </text>
</TEI>