<?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-01798801</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="2026-05-16T05:16:36+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Cheating a Parser to Death: Data-driven Cross-Treebank Annotation Transfer</title>
            <author role="aut">
              <persName>
                <forename type="first">Djamé</forename>
                <surname>Seddah</surname>
              </persName>
              <email type="md5">1a46dccff44eefe8ac69598e3b186e83</email>
              <email type="domain">paris-sorbonne.fr</email>
              <idno type="idhal" notation="string">djameseddah</idno>
              <idno type="idhal" notation="numeric">11545</idno>
              <idno type="halauthorid" notation="string">1878-11545</idno>
              <idno type="IDREF">https://www.idref.fr/086185136</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0194-8197</idno>
              <affiliation ref="#struct-123821"/>
              <affiliation ref="#struct-482775"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Éric</forename>
                <surname>Villemonte de La Clergerie</surname>
              </persName>
              <idno type="halauthorid">168296-0</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-482775"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Benoît</forename>
                <surname>Sagot</surname>
              </persName>
              <email type="md5">ef534712ca682bf74ec7eef17d3d1b5f</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">bsagot</idno>
              <idno type="idhal" notation="numeric">1461</idno>
              <idno type="halauthorid" notation="string">17075-1461</idno>
              <idno type="IDREF">https://www.idref.fr/177454229</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0107-8526</idno>
              <idno type="ARXIV">https://arxiv.org/a/sagot_b_1</idno>
              <idno type="GOOGLE SCHOLAR">HXUT9ZkAAAAJ</idno>
              <orgName ref="#struct-300009"/>
              <affiliation ref="#struct-482775"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hector</forename>
                <surname>Martinez Alonso</surname>
              </persName>
              <email type="md5">f6fa09f52ec5ce8ce0a5dea595f76fec</email>
              <email type="domain">inria.fr</email>
              <idno type="idhal" notation="string">hector-martinez-alonso</idno>
              <idno type="idhal" notation="numeric">12614</idno>
              <idno type="halauthorid" notation="string">32950-12614</idno>
              <idno type="IDREF">https://www.idref.fr/253131138</idno>
              <affiliation ref="#struct-476660"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Marie</forename>
                <surname>Candito</surname>
              </persName>
              <email type="md5">7ecb2efd6169b6577eee989107ccad3d</email>
              <email type="domain">gmail.com</email>
              <idno type="idhal" notation="string">marie-candito</idno>
              <idno type="idhal" notation="numeric">13596</idno>
              <idno type="halauthorid" notation="string">14130-13596</idno>
              <idno type="IDREF">https://www.idref.fr/153698616</idno>
              <idno type="ORCID">https://orcid.org/0000-0001-8306-4859</idno>
              <affiliation ref="#struct-1053"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Benoît</forename>
                <surname>Sagot</surname>
              </persName>
              <email type="md5">ef534712ca682bf74ec7eef17d3d1b5f</email>
              <email type="domain">inria.fr</email>
            </editor>
            <funder ref="#projanr-44644"/>
            <funder ref="#projanr-45801"/>
            <funder ref="#projanr-37982"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2018-05-23 23:13:29</date>
              <date type="whenModified">2025-09-12 17:04:02</date>
              <date type="whenReleased">2018-05-24 08:52:48</date>
              <date type="whenProduced">2018-05-07</date>
              <date type="whenEndEmbargoed">2018-05-23</date>
              <ref type="file" target="https://inria.hal.science/hal-01798801v1/document">
                <date notBefore="2018-05-23"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-01798801v1/file/1101.pdf" id="file-1798801-1825797">
                <date notBefore="2018-05-23"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="108708">
                <persName>
                  <forename>Benoît</forename>
                  <surname>Sagot</surname>
                </persName>
                <email type="md5">ef534712ca682bf74ec7eef17d3d1b5f</email>
                <email type="domain">inria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01798801</idno>
            <idno type="halUri">https://inria.hal.science/hal-01798801</idno>
            <idno type="halBibtex">seddah:hal-01798801</idno>
            <idno type="halRefHtml">&lt;i&gt;Eleventh International Conference on Language Resources and Evaluation (LREC 2018)&lt;/i&gt;, May 2018, Miyazaki, Japan</idno>
            <idno type="halRef">Eleventh International Conference on Language Resources and Evaluation (LREC 2018), May 2018, Miyazaki, Japan</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1798801-1825797"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-PARIS7" corresp="UNIV-PARIS">Université Denis Diderot - Paris VII</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-ROCQ">INRIA Paris - Rocquencourt</idno>
            <idno type="stamp" n="LLF">Laboratoire de Linguistique Formelle</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="USPC">Université Sorbonne Paris Cité</idno>
            <idno type="stamp" n="INRIA-300009">Inria 300009</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="UNIV-PARIS">Université Paris Cité</idno>
            <idno type="stamp" n="UP-SOCIETES-HUMANITES">Université Paris Cité - Faculté Sociétés et Humanités</idno>
            <idno type="stamp" n="SU-TI">Sorbonne Université - Texte Intégral</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="ALLIANCE-SU"> Alliance Sorbonne Université</idno>
            <idno type="stamp" n="INRIA-ETATSUNIS">Copublications Inria-Etats-Unis</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">Cheating a Parser to Death: Data-driven Cross-Treebank Annotation Transfer</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Djamé</forename>
                    <surname>Seddah</surname>
                  </persName>
                  <email type="md5">1a46dccff44eefe8ac69598e3b186e83</email>
                  <email type="domain">paris-sorbonne.fr</email>
                  <idno type="idhal" notation="string">djameseddah</idno>
                  <idno type="idhal" notation="numeric">11545</idno>
                  <idno type="halauthorid" notation="string">1878-11545</idno>
                  <idno type="IDREF">https://www.idref.fr/086185136</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0194-8197</idno>
                  <affiliation ref="#struct-123821"/>
                  <affiliation ref="#struct-482775"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Éric</forename>
                    <surname>Villemonte de La Clergerie</surname>
                  </persName>
                  <idno type="halauthorid">168296-0</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-482775"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Benoît</forename>
                    <surname>Sagot</surname>
                  </persName>
                  <email type="md5">ef534712ca682bf74ec7eef17d3d1b5f</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">bsagot</idno>
                  <idno type="idhal" notation="numeric">1461</idno>
                  <idno type="halauthorid" notation="string">17075-1461</idno>
                  <idno type="IDREF">https://www.idref.fr/177454229</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0107-8526</idno>
                  <idno type="ARXIV">https://arxiv.org/a/sagot_b_1</idno>
                  <idno type="GOOGLE SCHOLAR">HXUT9ZkAAAAJ</idno>
                  <orgName ref="#struct-300009"/>
                  <affiliation ref="#struct-482775"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hector</forename>
                    <surname>Martinez Alonso</surname>
                  </persName>
                  <email type="md5">f6fa09f52ec5ce8ce0a5dea595f76fec</email>
                  <email type="domain">inria.fr</email>
                  <idno type="idhal" notation="string">hector-martinez-alonso</idno>
                  <idno type="idhal" notation="numeric">12614</idno>
                  <idno type="halauthorid" notation="string">32950-12614</idno>
                  <idno type="IDREF">https://www.idref.fr/253131138</idno>
                  <affiliation ref="#struct-476660"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Marie</forename>
                    <surname>Candito</surname>
                  </persName>
                  <email type="md5">7ecb2efd6169b6577eee989107ccad3d</email>
                  <email type="domain">gmail.com</email>
                  <idno type="idhal" notation="string">marie-candito</idno>
                  <idno type="idhal" notation="numeric">13596</idno>
                  <idno type="halauthorid" notation="string">14130-13596</idno>
                  <idno type="IDREF">https://www.idref.fr/153698616</idno>
                  <idno type="ORCID">https://orcid.org/0000-0001-8306-4859</idno>
                  <affiliation ref="#struct-1053"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">LREC 2018</title>
                <meeting>
                  <title>Eleventh International Conference on Language Resources and Evaluation (LREC 2018)</title>
                  <date type="start">2018-05-07</date>
                  <date type="end">2018-05-12</date>
                  <settlement>Miyazaki</settlement>
                  <country key="JP">Japan</country>
                </meeting>
                <imprint>
                  <date type="datePub">2018-05</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Treebanking</term>
                <term xml:lang="en">Universal Dependencies</term>
                <term xml:lang="en">Syntax</term>
                <term xml:lang="en">Cross-annotation Transfer</term>
                <term xml:lang="en">Automatic Correction</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-cl">Computer Science [cs]/Computation and Language [cs.CL]</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>We present an efficient and accurate method for transferring annotations between two different treebanks of the same language. This method led to the creation of a new instance of the French Treebank (Abeillé et al., 2003), which follows the Universal Dependency annotation scheme and which was proposed to the participants of the CoNLL 2017 Universal Dependency parsing shared task (Zeman et al., 2017). Strong results from an evaluation on our gold standard (94.75% of LAS, 99.40% UAS on the test set) demonstrate the quality of this new annotated data set and validate our approach.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-123821" status="OLD">
          <idno type="IdRef">026403633</idno>
          <idno type="ISNI">000000012165487X</idno>
          <idno type="ROR">https://ror.org/02en5vm52</idno>
          <orgName>Université Paris-Sorbonne</orgName>
          <orgName type="acronym">UP4</orgName>
          <date type="start">1971-01-01</date>
          <date type="end">2017-12-31</date>
          <desc>
            <address>
              <addrLine>1 rue Victor Cousin - 75005 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.paris-sorbonne.fr/</ref>
          </desc>
        </org>
        <org type="researchteam" xml:id="struct-482775" status="VALID">
          <idno type="RNSR">201722248N</idno>
          <idno type="ROR">https://ror.org/05rnwy495</idno>
          <orgName>Automatic Language Modelling and ANAlysis &amp; Computational Humanities</orgName>
          <orgName type="acronym">ALMAnaCH</orgName>
          <date type="start">2017-01-01</date>
          <date type="end">2029-04-30</date>
          <desc>
            <address>
              <addrLine>48 Rue Barrault, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.inria.fr/equipes/almanach</ref>
          </desc>
          <listRelation>
            <relation active="#struct-454310" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-476660" status="VALID">
          <orgName>Thomson Reuters</orgName>
          <desc>
            <address>
              <country key="US"/>
            </address>
            <ref type="url">https://www.thomsonreuters.com/en.html</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-1053" status="OLD">
          <idno type="IdRef">026390574</idno>
          <idno type="RNSR">200112497J</idno>
          <idno type="ROR">https://ror.org/0223bz716</idno>
          <orgName>Laboratoire de Linguistique Formelle</orgName>
          <orgName type="acronym">LLF UMR7110</orgName>
          <date type="start">1972-01-01</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Case Postale 7031 5, rue Thomas Mann 75205 Paris cedex 13</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.llf.cnrs.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300301" type="direct"/>
            <relation name="UMR7110" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-454310" status="VALID">
          <idno type="IdRef">241614864</idno>
          <idno type="RNSR">196718247G</idno>
          <idno type="ROR">https://ror.org/05eyd5d35</idno>
          <orgName>Centre Inria de Paris</orgName>
          <date type="start">2016-03-10</date>
          <desc>
            <address>
              <addrLine>48 Rue Barrault, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/paris</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" 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="institution" xml:id="struct-300301" status="OLD">
          <idno type="IdRef">027542084</idno>
          <idno type="ISNI">0000000121514068</idno>
          <idno type="ROR">https://ror.org/02n7qrg46</idno>
          <orgName>Université Paris Diderot - Paris 7</orgName>
          <orgName type="acronym">UPD7</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>5 rue Thomas-Mann - 75205 Paris cedex 13</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-paris-diderot.fr</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>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-44644" status="VALID">
          <idno type="anr">ANR-16-CE33-0021</idno>
          <orgName>PARSITI</orgName>
          <desc>Analyser l'impossible, Traduire l'improbable</desc>
          <date type="start">2016</date>
        </org>
        <org type="anrProject" xml:id="projanr-45801" status="VALID">
          <idno type="anr">ANR-15-CE38-0011</idno>
          <orgName>SoSweet</orgName>
          <desc>Une sociolinguistique de Twitter : liens sociaux et variations linguistiques</desc>
          <date type="start">2015</date>
        </org>
        <org type="anrProject" xml:id="projanr-37982" status="VALID">
          <idno type="anr">ANR-11-IDEX-0005</idno>
          <orgName>USPC</orgName>
          <desc>Université Sorbonne Paris Cité</desc>
          <date type="start">2011</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>