<?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-00117473</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="2026-05-19T15:20:13+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Using the Structure of Documents to Improve the Discovery of Unexpected Information</title>
            <author role="aut">
              <persName>
                <forename type="first">François</forename>
                <surname>Jacquenet</surname>
              </persName>
              <email type="md5">aeb9a67b85b63d5de9ea5be6187c0a41</email>
              <email type="domain">univ-st-etienne.fr</email>
              <idno type="idhal" notation="string">francois-jacquenet</idno>
              <idno type="idhal" notation="numeric">7550</idno>
              <idno type="halauthorid" notation="string">179081-7550</idno>
              <idno type="IDREF">https://www.idref.fr/130579645</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0653-0710</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>François</forename>
                <surname>Jacquenet</surname>
              </persName>
              <email type="md5">aeb9a67b85b63d5de9ea5be6187c0a41</email>
              <email type="domain">univ-st-etienne.fr</email>
            </editor>
            <funder>Financement ANR (ACI Masses de Données)</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2006-12-01 17:34:33</date>
              <date type="whenModified">2026-04-23 14:50:04</date>
              <date type="whenReleased">2006-12-01 17:34:33</date>
              <date type="whenProduced">2006-04-23</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="114933">
                <persName>
                  <forename>François</forename>
                  <surname>Jacquenet</surname>
                </persName>
                <email type="md5">aeb9a67b85b63d5de9ea5be6187c0a41</email>
                <email type="domain">univ-st-etienne.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00117473</idno>
            <idno type="halUri">https://hal.science/hal-00117473</idno>
            <idno type="halBibtex">jacquenet:hal-00117473</idno>
            <idno type="halRefHtml">Apr 2006, pp.1036-1042</idno>
            <idno type="halRef">Apr 2006, pp.1036-1042</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-ST-ETIENNE">Université Jean Monnet - 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="UDL">UDL</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="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">Using the Structure of Documents to Improve the Discovery of Unexpected Information</title>
                <author role="aut">
                  <persName>
                    <forename type="first">François</forename>
                    <surname>Jacquenet</surname>
                  </persName>
                  <email type="md5">aeb9a67b85b63d5de9ea5be6187c0a41</email>
                  <email type="domain">univ-st-etienne.fr</email>
                  <idno type="idhal" notation="string">francois-jacquenet</idno>
                  <idno type="idhal" notation="numeric">7550</idno>
                  <idno type="halauthorid" notation="string">179081-7550</idno>
                  <idno type="IDREF">https://www.idref.fr/130579645</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0653-0710</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>
                <title level="m">Proceedings of the 2006 ACM Symposium on Applied Computing (SAC)</title>
                <meeting>
                  <date type="start">2006-04-23</date>
                </meeting>
                <imprint>
                  <publisher>ACM Press</publisher>
                  <biblScope unit="pp">1036-1042</biblScope>
                  <date type="datePub">2006-04-23</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-ir">Computer Science [cs]/Information Retrieval [cs.IR]</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>In this paper we are interested in taking into account the structure of the documents during the discovery of unexpected information in textual databases. Following a work that aimed at designing and integrating, in the UnexpectedMiner system, some measures for the evaluation of the unexpectedness of documents, we wanted to improve the system by taking into account the structure of the documents processed. Each part of the documents are weighted by some coefficients whose values are determined by optimization techniques. Those coefficients are then used by the system in the unexpectedness measures to determine if a document contains some unexpected information or not. The efficiency of our new system is then evaluated and the experiments put forward the improvements induced by the use of the structure of the documents.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <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="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>