<?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-05339398</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="2026-05-21T12:07:05+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Subgraph-induced Extraction Technique for Information (SETI) from Administrative Documents</title>
            <author role="aut">
              <persName>
                <forename type="first">Dipendra</forename>
                <surname>Sharma Kafle</surname>
              </persName>
              <email type="md5">ddc25c07857d9d2be52d14469e150d8c</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="numeric">1600960</idno>
              <idno type="halauthorid" notation="string">3219475-1600960</idno>
              <affiliation ref="#struct-40831"/>
              <affiliation ref="#struct-239784"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Eliott</forename>
                <surname>Thomas</surname>
              </persName>
              <email type="md5">7ad742d2fe6335de4b77edc70c258f2c</email>
              <email type="domain">protonmail.com</email>
              <idno type="idhal" notation="string">eliott-thomas</idno>
              <idno type="idhal" notation="numeric">1409659</idno>
              <idno type="halauthorid" notation="string">3219476-1409659</idno>
              <idno type="ORCID">https://orcid.org/0009-0008-5266-8797</idno>
              <affiliation ref="#struct-40831"/>
              <affiliation ref="#struct-1165815"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mickael</forename>
                <surname>Coustaty</surname>
              </persName>
              <email type="md5">f9ce53d60edb2cd05a382789958ad267</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="string">mickael-coustaty</idno>
              <idno type="idhal" notation="numeric">2462</idno>
              <idno type="halauthorid" notation="string">2084236-2462</idno>
              <idno type="IDREF">https://www.idref.fr/160560268</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0123-439X</idno>
              <affiliation ref="#struct-40831"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Aurélie</forename>
                <surname>Joseph</surname>
              </persName>
              <idno type="halauthorid">1047656-0</idno>
              <affiliation ref="#struct-524544"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Antoine</forename>
                <surname>Doucet</surname>
              </persName>
              <email type="md5">6825953aaa4e1a7f1891ff65fb5b42f5</email>
              <email type="domain">univ-lr.fr</email>
              <idno type="idhal" notation="string">antoine-doucet</idno>
              <idno type="idhal" notation="numeric">7183</idno>
              <idno type="halauthorid" notation="string">23275-7183</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-6160-3356</idno>
              <idno type="IDREF">https://www.idref.fr/10312604X</idno>
              <affiliation ref="#struct-40831"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Vincent</forename>
                <surname>Poulain d'Andecy</surname>
              </persName>
              <idno type="halauthorid">604463-0</idno>
              <affiliation ref="#struct-524544"/>
              <affiliation ref="#struct-40831"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Dipendra</forename>
                <surname>Sharma Kafle</surname>
              </persName>
              <email type="md5">8bc2be6a88bc289fc17ddd9a17fbd145</email>
              <email type="domain">gmail.com</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-10-30 18:03:04</date>
              <date type="whenModified">2025-11-04 16:23:57</date>
              <date type="whenReleased">2025-11-04 16:23:57</date>
              <date type="whenProduced">2023-08-21</date>
              <date type="whenEndEmbargoed">2025-10-30</date>
              <ref type="file" target="https://univ-rochelle.hal.science/hal-05339398v1/document">
                <date notBefore="2025-10-30"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://univ-rochelle.hal.science/hal-05339398v1/file/ICDAR23.pdf" id="file-5339398-4571122">
                <date notBefore="2025-10-30"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1413897">
                <persName>
                  <forename>Dipendra</forename>
                  <surname>Sharma Kafle</surname>
                </persName>
                <email type="md5">8bc2be6a88bc289fc17ddd9a17fbd145</email>
                <email type="domain">gmail.com</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05339398</idno>
            <idno type="halUri">https://univ-rochelle.hal.science/hal-05339398</idno>
            <idno type="halBibtex">sharmakafle:hal-05339398</idno>
            <idno type="halRefHtml">&lt;i&gt;Document Analysis and Recognition - ICDAR 2023&lt;/i&gt;, Aug 2023, San José, CA, USA, United States</idno>
            <idno type="halRef">Document Analysis and Recognition - ICDAR 2023, Aug 2023, San José, CA, USA, United States</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-5339398-4571122"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-ROCHELLE">Université de La Rochelle</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Subgraph-induced Extraction Technique for Information (SETI) from Administrative Documents</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Dipendra</forename>
                    <surname>Sharma Kafle</surname>
                  </persName>
                  <email type="md5">ddc25c07857d9d2be52d14469e150d8c</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="numeric">1600960</idno>
                  <idno type="halauthorid" notation="string">3219475-1600960</idno>
                  <affiliation ref="#struct-40831"/>
                  <affiliation ref="#struct-239784"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Eliott</forename>
                    <surname>Thomas</surname>
                  </persName>
                  <email type="md5">7ad742d2fe6335de4b77edc70c258f2c</email>
                  <email type="domain">protonmail.com</email>
                  <idno type="idhal" notation="string">eliott-thomas</idno>
                  <idno type="idhal" notation="numeric">1409659</idno>
                  <idno type="halauthorid" notation="string">3219476-1409659</idno>
                  <idno type="ORCID">https://orcid.org/0009-0008-5266-8797</idno>
                  <affiliation ref="#struct-40831"/>
                  <affiliation ref="#struct-1165815"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mickael</forename>
                    <surname>Coustaty</surname>
                  </persName>
                  <email type="md5">f9ce53d60edb2cd05a382789958ad267</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="string">mickael-coustaty</idno>
                  <idno type="idhal" notation="numeric">2462</idno>
                  <idno type="halauthorid" notation="string">2084236-2462</idno>
                  <idno type="IDREF">https://www.idref.fr/160560268</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0123-439X</idno>
                  <affiliation ref="#struct-40831"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Aurélie</forename>
                    <surname>Joseph</surname>
                  </persName>
                  <idno type="halauthorid">1047656-0</idno>
                  <affiliation ref="#struct-524544"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Antoine</forename>
                    <surname>Doucet</surname>
                  </persName>
                  <email type="md5">6825953aaa4e1a7f1891ff65fb5b42f5</email>
                  <email type="domain">univ-lr.fr</email>
                  <idno type="idhal" notation="string">antoine-doucet</idno>
                  <idno type="idhal" notation="numeric">7183</idno>
                  <idno type="halauthorid" notation="string">23275-7183</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-6160-3356</idno>
                  <idno type="IDREF">https://www.idref.fr/10312604X</idno>
                  <affiliation ref="#struct-40831"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Vincent</forename>
                    <surname>Poulain d'Andecy</surname>
                  </persName>
                  <idno type="halauthorid">604463-0</idno>
                  <affiliation ref="#struct-524544"/>
                  <affiliation ref="#struct-40831"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>Document Analysis and Recognition - ICDAR 2023</title>
                  <date type="start">2023-08-21</date>
                  <settlement>San José, CA, USA</settlement>
                  <country key="US">United States</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Graph Neural Network</term>
                <term xml:lang="en">Invoice</term>
                <term xml:lang="en">Information Extraction</term>
                <term xml:lang="en">Information Extraction Invoice Graph Neural Network</term>
              </keywords>
              <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>&lt;div&gt;&lt;p&gt;Information Extraction plays a key role in the automation of auditing processes in administrative documents. However, variety in layout and language is always a challenging task. On the other hand, large volumes of public training datasets related to administrative documents such as invoices are rare to find. In this work, we use Graph Attention Network model for information extraction. This type of model makes it easier to understand the mechanism as compared to classical neural networks due to the visualization of link between entities in the graph. Moreover, it maximizes the layout and structure retrieval which is a crucial advantage in administrative documents. From the same graph, our model learns at different graph levels to encapsulate dynamic and more enriched knowledge in each batch, thus maximizing the generalization on smaller dataset. We present how the model learns in each graph level and compare the results with baselines on private as well as public datasets. Our model succeeds in improving recall and precision scores for some classes in our private dataset and produces comparable results for public datasets designed for Form Understanding and Information Extraction.&lt;/p&gt;&lt;/div&gt;</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-40831" status="VALID">
          <idno type="IdRef">183449045</idno>
          <idno type="RNSR">199613735B</idno>
          <idno type="ROR">https://ror.org/03r7r0k94</idno>
          <orgName>Laboratoire Informatique, Image et Interaction - EA 2118</orgName>
          <orgName type="acronym">L3I</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Pascal Avenue Michel Crépeau F-17042 La Rochelle Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://l3i.univ-larochelle.fr/</ref>
          </desc>
          <listRelation>
            <relation name="EA2118" active="#struct-300311" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-239784" status="VALID">
          <orgName>École d'Ingénieurs en Génie des Systèmes Industriels [La Rochelle]</orgName>
          <orgName type="acronym">EIGSI</orgName>
          <desc>
            <address>
              <addrLine>26 rue de Vaux de Foletier 17041 La Rochelle cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.eigsi.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-362830" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1165815" status="INCOMING">
          <orgName>Yooz</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-524544" status="INCOMING">
          <orgName>Yooz ITESOFT-Yooz Group</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300311" status="VALID">
          <idno type="IdRef">035375043</idno>
          <idno type="ISNI">0000 0001 2169 7335</idno>
          <idno type="ROR">https://ror.org/04mv1z119</idno>
          <orgName>La Rochelle Université</orgName>
          <orgName type="acronym">ULR</orgName>
          <desc>
            <address>
              <addrLine>Technoforum - 23 avenue Albert Einstein - BP 33060 - 17031 La Rochelle - France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-larochelle.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-362830" status="VALID">
          <orgName>Ecole d'Ingénieurs en Génie des Systèmes Industriels</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.eigsi.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>