<?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-05215557</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="2026-05-11T06:36:14+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Extracting Structured Requirements from Unstructured Building Technical Specifications for Building Information Modeling</title>
            <author role="aut">
              <persName>
                <forename type="first">Insaf</forename>
                <surname>Nahri</surname>
              </persName>
              <idno type="halauthorid">3601836-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Romain</forename>
                <surname>Pinquié</surname>
              </persName>
              <email type="md5">af23c3790e5f6cc02583b9dd21254583</email>
              <email type="domain">grenoble-inp.fr</email>
              <idno type="idhal" notation="string">rpinquie</idno>
              <idno type="idhal" notation="numeric">9987</idno>
              <idno type="halauthorid" notation="string">31526-9987</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-5913-4714</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=bW-DFWEAAAAJ&amp;hl=fr</idno>
              <idno type="IDREF">https://www.idref.fr/196824605</idno>
              <affiliation ref="#struct-1043137"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Philippe</forename>
                <surname>Véron</surname>
              </persName>
              <email type="md5">722ab5e0fcd171501b559321119ca130</email>
              <email type="domain">ensam.eu</email>
              <idno type="idhal" notation="string">philippeveron</idno>
              <idno type="idhal" notation="numeric">1183737</idno>
              <idno type="halauthorid" notation="string">243063-1183737</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4062-2432</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=qZ6InYkAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/112481841</idno>
              <idno type="VIAF">https://viaf.org/viaf/191824140</idno>
              <affiliation ref="#struct-301320"/>
              <affiliation ref="#struct-543315"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Nicolas</forename>
                <surname>Bus</surname>
              </persName>
              <idno type="halauthorid">41576-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Mathieu</forename>
                <surname>Thorel</surname>
              </persName>
              <idno type="halauthorid">1080846-0</idno>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Pinquié</forename>
                <surname>Romain</surname>
              </persName>
              <email type="md5">af23c3790e5f6cc02583b9dd21254583</email>
              <email type="domain">grenoble-inp.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2025-08-20 08:26:01</date>
              <date type="whenModified">2026-03-27 10:22:03</date>
              <date type="whenReleased">2025-08-20 08:26:01</date>
              <date type="whenProduced">2025-08-20</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="179244">
                <persName>
                  <forename>Pinquié</forename>
                  <surname>Romain</surname>
                </persName>
                <email type="md5">af23c3790e5f6cc02583b9dd21254583</email>
                <email type="domain">grenoble-inp.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05215557</idno>
            <idno type="halUri">https://hal.science/hal-05215557</idno>
            <idno type="halBibtex">nahri:hal-05215557</idno>
            <idno type="halRefHtml">2025</idno>
            <idno type="halRef">2025</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UGA">HAL Grenoble Alpes</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="ENSAM">Arts et Métiers Sciences et Technologies</idno>
            <idno type="stamp" n="INPG">Institut polytechnique de Grenoble</idno>
            <idno type="stamp" n="G-SCOP">LABORATOIRE G-SCOP</idno>
            <idno type="stamp" n="UGA-EPE">Université Grenoble Alpes [2020-*]</idno>
            <idno type="stamp" n="HESAM">Hesam</idno>
            <idno type="stamp" n="HESAM-ENSAM" corresp="HESAM">Ecole Nationale Supérieure d'Arts et Métiers - Hesam</idno>
            <idno type="stamp" n="LISPEN" corresp="ENSAM"> Laboratoire d'Ingénierie des Systèmes Physiques et Numériques</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Extracting Structured Requirements from Unstructured Building Technical Specifications for Building Information Modeling</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Insaf</forename>
                    <surname>Nahri</surname>
                  </persName>
                  <idno type="halauthorid">3601836-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Romain</forename>
                    <surname>Pinquié</surname>
                  </persName>
                  <email type="md5">af23c3790e5f6cc02583b9dd21254583</email>
                  <email type="domain">grenoble-inp.fr</email>
                  <idno type="idhal" notation="string">rpinquie</idno>
                  <idno type="idhal" notation="numeric">9987</idno>
                  <idno type="halauthorid" notation="string">31526-9987</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-5913-4714</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=bW-DFWEAAAAJ&amp;hl=fr</idno>
                  <idno type="IDREF">https://www.idref.fr/196824605</idno>
                  <affiliation ref="#struct-1043137"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Philippe</forename>
                    <surname>Véron</surname>
                  </persName>
                  <email type="md5">722ab5e0fcd171501b559321119ca130</email>
                  <email type="domain">ensam.eu</email>
                  <idno type="idhal" notation="string">philippeveron</idno>
                  <idno type="idhal" notation="numeric">1183737</idno>
                  <idno type="halauthorid" notation="string">243063-1183737</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4062-2432</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=qZ6InYkAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/112481841</idno>
                  <idno type="VIAF">https://viaf.org/viaf/191824140</idno>
                  <affiliation ref="#struct-301320"/>
                  <affiliation ref="#struct-543315"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Nicolas</forename>
                    <surname>Bus</surname>
                  </persName>
                  <idno type="halauthorid">41576-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Mathieu</forename>
                    <surname>Thorel</surname>
                  </persName>
                  <idno type="halauthorid">1080846-0</idno>
                </author>
              </analytic>
              <monogr>
                <imprint>
                  <date type="datePub">2025</date>
                </imprint>
              </monogr>
              <idno type="doi">10.48550/arXiv.2508.13833</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Building Information Modeling</term>
                <term xml:lang="en">Natural Language Processing</term>
                <term xml:lang="en">Construction Industry</term>
                <term xml:lang="en">Information Extraction</term>
                <term xml:lang="en">Named Entity Recognition</term>
                <term xml:lang="en">Relation Extraction</term>
                <term xml:lang="en">Automated Code Checking</term>
                <term xml:lang="en">Unstructured Data</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halOldTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halTreeTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>This study explores the integration of Building Information Modeling (BIM) with Natural Language Processing (NLP) to automate the extraction of requirements from unstructured French Building Technical Specification (BTS) documents within the construction industry. Employing Named Entity Recognition (NER) and Relation Extraction (RE) techniques, the study leverages the transformer-based model CamemBERT and applies transfer learning with the French language model Fr\_core\_news\_lg, both pre-trained on a large French corpus in the general domain. To benchmark these models, additional approaches ranging from rule-based to deep learning-based methods are developed. For RE, four different supervised models, including Random Forest, are implemented using a custom feature vector. A hand-crafted annotated dataset is used to compare the effectiveness of NER approaches and RE models. Results indicate that CamemBERT and Fr\_core\_news\_lg exhibited superior performance in NER, achieving F1-scores over 90\%, while Random Forest proved most effective in RE, with an F1 score above 80\%. The outcomes are intended to be represented as a knowledge graph in future work to further enhance automatic verification systems.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1043137" status="VALID">
          <idno type="IdRef">120293080</idno>
          <idno type="ISNI">0000 0004 7645 579X</idno>
          <idno type="RNSR">200919221H</idno>
          <idno type="ROR">00rv5x925</idno>
          <orgName>Laboratoire des sciences pour la conception, l'optimisation et la production</orgName>
          <orgName type="acronym">G-SCOP</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>GSCOP, Laboratoire des Sciences pour la Conception, l'Optimisation et la Production de Grenoble, UMR 527246, avenue Félix Viallet - 38031 Grenoble Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.g-scop.grenoble-inp.fr/</ref>
          </desc>
          <listRelation>
            <relation name="UMR5272" active="#struct-441569" type="direct"/>
            <relation active="#struct-1042703" type="direct"/>
            <relation active="#struct-1043329" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-301320" status="OLD">
          <orgName>École Nationale Supérieure d'Arts et Métiers</orgName>
          <orgName type="acronym">ENSAM</orgName>
          <date type="end">2020-03-04</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://artsetmetiers.fr/fr</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-543315" status="VALID">
          <idno type="IdRef">23435822X</idno>
          <idno type="RNSR">201722624X</idno>
          <idno type="ROR">https://ror.org/055449294</idno>
          <orgName>Laboratoire d’Ingénierie des Systèmes Physiques et Numériques</orgName>
          <orgName type="acronym">LISPEN</orgName>
          <desc>
            <address>
              <addrLine>F-13617 Aix-en-Provence                              F-71100 Chalon-Sur-Saône                                        F-59000 Lille</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://lispen.artsetmetiers.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1003434" type="direct"/>
          </listRelation>
        </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>
        <org type="regroupinstitution" xml:id="struct-1042703" status="VALID">
          <idno type="IdRef">240648315</idno>
          <idno type="ROR">https://ror.org/02rx3b187</idno>
          <orgName>Université Grenoble Alpes</orgName>
          <orgName type="acronym">UGA</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Adresse CS 40700 - 38058 Grenoble cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-grenoble-alpes.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-1043329" status="VALID">
          <idno type="IdRef">026388804</idno>
          <idno type="ROR">https://ror.org/05sbt2524</idno>
          <orgName>Institut polytechnique de Grenoble - Grenoble Institute of Technology</orgName>
          <orgName type="acronym">Grenoble INP</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>46 avenue Félix Viallet 38031 Grenoble Cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.grenoble-inp.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1042703" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1003434" status="VALID">
          <idno type="IdRef">02637515X</idno>
          <idno type="ISNI">0000000121946047</idno>
          <idno type="ROR">https://ror.org/018pp1107</idno>
          <idno type="Wikidata">Q2570220</idno>
          <orgName>Arts et Métiers Sciences et Technologies</orgName>
          <date type="start">2020-03-04</date>
          <desc>
            <address>
              <addrLine>151 boulevard de l'Hôpital 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://artsetmetiers.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>