<?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-03852052</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="2026-05-21T13:16:03+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">A novel pattern-based edit distance for automatic log parsing</title>
            <author role="aut">
              <persName>
                <forename type="first">Maxime</forename>
                <surname>Raynal</surname>
              </persName>
              <email type="md5">b148ad33b1db254913f1a9553ec99ae0</email>
              <email type="domain">nokia.com</email>
              <idno type="idhal" notation="string">maxime-raynal</idno>
              <idno type="idhal" notation="numeric">754218</idno>
              <idno type="halauthorid" notation="string">50241-754218</idno>
              <affiliation ref="#struct-446305"/>
              <affiliation ref="#struct-1043317"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marc-Olivier</forename>
                <surname>Buob</surname>
              </persName>
              <email type="md5">67c8884331e63c5d8a12ac1f8e94d5a4</email>
              <email type="domain">orange.fr</email>
              <idno type="idhal" notation="string">marc-olivier-buob</idno>
              <idno type="idhal" notation="numeric">13666</idno>
              <idno type="halauthorid" notation="string">6246-13666</idno>
              <idno type="IDREF">https://www.idref.fr/142541575</idno>
              <affiliation ref="#struct-446305"/>
              <affiliation ref="#struct-160294"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Georges</forename>
                <surname>Quénot</surname>
              </persName>
              <email type="md5">6de4f020df3f46acfcb287ef4ffafa0f</email>
              <email type="domain">imag.fr</email>
              <idno type="idhal" notation="string">georges-quenot</idno>
              <idno type="idhal" notation="numeric">3114</idno>
              <idno type="halauthorid" notation="string">16648-3114</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-2117-247X</idno>
              <idno type="IDREF">https://www.idref.fr/034104518</idno>
              <affiliation ref="#struct-1043317"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Marc-Olivier</forename>
                <surname>Buob</surname>
              </persName>
              <email type="md5">67c8884331e63c5d8a12ac1f8e94d5a4</email>
              <email type="domain">orange.fr</email>
            </editor>
            <funder ref="#projanr-50501"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2022-11-14 17:38:34</date>
              <date type="whenModified">2026-01-19 16:46:20</date>
              <date type="whenReleased">2022-12-05 09:43:09</date>
              <date type="whenProduced">2022-08-21</date>
              <date type="whenEndEmbargoed">2022-11-14</date>
              <ref type="file" target="https://hal.science/hal-03852052v1/document">
                <date notBefore="2022-11-14"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-03852052v1/file/ICPR_2022.pdf" id="file-3852052-3397755">
                <date notBefore="2022-11-14"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="524475">
                <persName>
                  <forename>Marc-Olivier</forename>
                  <surname>Buob</surname>
                </persName>
                <email type="md5">67c8884331e63c5d8a12ac1f8e94d5a4</email>
                <email type="domain">orange.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03852052</idno>
            <idno type="halUri">https://hal.science/hal-03852052</idno>
            <idno type="halBibtex">raynal:hal-03852052</idno>
            <idno type="halRefHtml">&lt;i&gt;26th International Conference on Pattern Recognition (ICPR)&lt;/i&gt;, Aug 2022, Montréal, Canada. &lt;a target="_blank" href="https://dx.doi.org/10.1109/ICPR56361.2022.9956295"&gt;&amp;#x27E8;10.1109/ICPR56361.2022.9956295&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">26th International Conference on Pattern Recognition (ICPR), Aug 2022, Montréal, Canada. &amp;#x27E8;10.1109/ICPR56361.2022.9956295&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3852052-3397755"/></licence>
            </availability>
          </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="INPG">Institut polytechnique de Grenoble</idno>
            <idno type="stamp" n="LIG">Laboratoire d'Informatique de Grenoble</idno>
            <idno type="stamp" n="LIG_TDCGE_MRIM" corresp="LIG_TDCGE">MRIM</idno>
            <idno type="stamp" n="SORBONNE-UNIVERSITE">Sorbonne Université</idno>
            <idno type="stamp" n="SORBONNE-UNIV" corresp="SORBONNE-UNIVERSITE">Sorbonne Université 01/01/2018</idno>
            <idno type="stamp" n="INSTITUTS-TELECOM">composantes instituts telecom </idno>
            <idno type="stamp" n="MIAI">Multidisciplinary Institute in Artificial intelligence - Grenoble Alpes</idno>
            <idno type="stamp" n="PNRIA">Programme National de Recherche en IA</idno>
            <idno type="stamp" n="UGA-EPE">Université Grenoble Alpes [2020-*]</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="LIG_SIDCH" corresp="LIG">Systèmes intelligents pour les données, les connaissances et les humains</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="ANR-IA-19" corresp="ANR-IA">ANR-IA-19</idno>
            <idno type="stamp" n="ANR-IA">ANR-IA</idno>
            <idno type="stamp" n="TEST-UGA">TEST-UGA</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">A novel pattern-based edit distance for automatic log parsing</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Maxime</forename>
                    <surname>Raynal</surname>
                  </persName>
                  <email type="md5">b148ad33b1db254913f1a9553ec99ae0</email>
                  <email type="domain">nokia.com</email>
                  <idno type="idhal" notation="string">maxime-raynal</idno>
                  <idno type="idhal" notation="numeric">754218</idno>
                  <idno type="halauthorid" notation="string">50241-754218</idno>
                  <affiliation ref="#struct-446305"/>
                  <affiliation ref="#struct-1043317"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marc-Olivier</forename>
                    <surname>Buob</surname>
                  </persName>
                  <email type="md5">67c8884331e63c5d8a12ac1f8e94d5a4</email>
                  <email type="domain">orange.fr</email>
                  <idno type="idhal" notation="string">marc-olivier-buob</idno>
                  <idno type="idhal" notation="numeric">13666</idno>
                  <idno type="halauthorid" notation="string">6246-13666</idno>
                  <idno type="IDREF">https://www.idref.fr/142541575</idno>
                  <affiliation ref="#struct-446305"/>
                  <affiliation ref="#struct-160294"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Georges</forename>
                    <surname>Quénot</surname>
                  </persName>
                  <email type="md5">6de4f020df3f46acfcb287ef4ffafa0f</email>
                  <email type="domain">imag.fr</email>
                  <idno type="idhal" notation="string">georges-quenot</idno>
                  <idno type="idhal" notation="numeric">3114</idno>
                  <idno type="halauthorid" notation="string">16648-3114</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-2117-247X</idno>
                  <idno type="IDREF">https://www.idref.fr/034104518</idno>
                  <affiliation ref="#struct-1043317"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">2022 26th International Conference on Pattern Recognition (ICPR)</title>
                <meeting>
                  <title>26th International Conference on Pattern Recognition (ICPR)</title>
                  <date type="start">2022-08-21</date>
                  <settlement>Montréal</settlement>
                  <country key="CA">Canada</country>
                </meeting>
                <imprint>
                  <date type="datePub">2022-08</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/ICPR56361.2022.9956295</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-ds">Computer Science [cs]/Data Structures and Algorithms [cs.DS]</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>This work aims at inferring a set of regular expressions to parse a text file, like a system log. To this end, we propose a novel edit distance taking advantage of the pattern matching background. Edit distances are commonly used for fuzzy search and in bioinformatics, and compare two strings at the character level. By doing so, edit distances do not consider the nature of the data conveyed by the strings. To address this problem, we propose the following contributions. First, we propose to model strings at the pattern level using a dedicated data structure, called pattern automaton. Second, we design a novel edit distance, operating at the pattern level. Third, we derive a clustering algorithm optimized for this distance. Finally, we evaluate our proposal through experimental validation.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-446305" status="VALID">
          <orgName>Nokia Bell Labs [Nozay]</orgName>
          <desc>
            <address>
              <addrLine>Route de Villejust91620 Nozay</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.bell-labs.com/connect/global-locations/france/</ref>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-1043317" status="VALID">
          <orgName>Modélisation et Recherche d’Information Multimédia [Grenoble]</orgName>
          <orgName type="acronym">MRIM</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>Laboratoire LIG - Bâtiment IMAG - 700 avenue Centrale, CS 40700 - 38058 Grenoble cedex 9</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://lig-mrim.imag.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-1043301" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation name="UMR5217" active="#struct-441569" type="indirect"/>
            <relation active="#struct-1042703" type="indirect"/>
            <relation active="#struct-1043329" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-160294" status="OLD">
          <orgName>Laboratory of Information, Network and Communication Sciences</orgName>
          <orgName type="acronym">LINCS</orgName>
          <desc>
            <address>
              <addrLine>23 avenue d'Italie 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.lincs.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-93591" type="direct"/>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-302102" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1043301" status="VALID">
          <idno type="IdRef">148425550</idno>
          <idno type="ISNI">0000 0001 2286 4035</idno>
          <idno type="RNSR">200711886U</idno>
          <idno type="ROR">https://ror.org/01c8rcg82</idno>
          <orgName>Laboratoire d'Informatique de Grenoble</orgName>
          <orgName type="acronym">LIG</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>UMR 5217 - Laboratoire LIG - Bâtiment IMAG - 700 avenue Centrale - Domaine Universitaire de Saint-Martin-d’Hères Adresse postale : CS 40700 - 38058 Grenoble cedex 9Tél. : 04 57 42 14 00</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.liglab.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
            <relation name="UMR5217" 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-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="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-93591" status="OLD">
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Université Pierre et Marie Curie - Paris 6</orgName>
          <orgName type="acronym">UPMC</orgName>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>4 place Jussieu - 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.upmc.fr/</ref>
          </desc>
        </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>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-50501" status="VALID">
          <idno type="anr">ANR-19-P3IA-0003</idno>
          <orgName>MIAI</orgName>
          <desc>MIAI @ Grenoble Alpes</desc>
          <date type="start">2019</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>