<?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-00484294</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="2026-05-17T07:01:14+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Influence of Pre-annotation on POS-tagged Corpus Development</title>
            <author role="aut">
              <persName>
                <forename type="first">Karen</forename>
                <surname>Fort</surname>
              </persName>
              <email type="md5">24fcc09edce5cbf8df003845469f6b01</email>
              <email type="domain">loria.fr</email>
              <idno type="idhal" notation="string">karen-fort</idno>
              <idno type="idhal" notation="numeric">2215</idno>
              <idno type="halauthorid" notation="string">240168-2215</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-0723-8850</idno>
              <idno type="IDREF">https://www.idref.fr/176299548</idno>
              <affiliation ref="#struct-1814"/>
              <affiliation ref="#struct-994"/>
            </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>
              <affiliation ref="#struct-54505"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Karën</forename>
                <surname>Fort</surname>
              </persName>
              <email type="md5">24fcc09edce5cbf8df003845469f6b01</email>
              <email type="domain">loria.fr</email>
            </editor>
            <funder>Quaero (en partie)</funder>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2010-05-18 11:40:01</date>
              <date type="whenWritten">2010-05-11</date>
              <date type="whenModified">2025-02-26 15:24:03</date>
              <date type="whenReleased">2010-05-18 14:40:44</date>
              <date type="whenProduced">2010-07-15</date>
              <date type="whenEndEmbargoed">2010-05-18</date>
              <ref type="file" target="https://hal.science/hal-00484294v1/document">
                <date notBefore="2010-05-18"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-00484294v1/file/lawiv_KFBS_preannot.pdf" id="file-484294-625920">
                <date notBefore="2010-05-18"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="120226">
                <persName>
                  <forename>Karën</forename>
                  <surname>Fort</surname>
                </persName>
                <email type="md5">24fcc09edce5cbf8df003845469f6b01</email>
                <email type="domain">loria.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00484294</idno>
            <idno type="halUri">https://hal.science/hal-00484294</idno>
            <idno type="halBibtex">fort:hal-00484294</idno>
            <idno type="halRefHtml">&lt;i&gt;The Fourth ACL Linguistic Annotation Workshop&lt;/i&gt;, Jul 2010, Uppsala, Sweden. pp.56-63</idno>
            <idno type="halRef">The Fourth ACL Linguistic Annotation Workshop, Jul 2010, Uppsala, Sweden. pp.56-63</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-484294-625920"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-PARIS7" corresp="UNIV-PARIS">Université Denis Diderot - Paris VII</idno>
            <idno type="stamp" n="UNIV-PARIS13">Université Paris-Nord - Paris XIII </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="OCA">Observatoire de la Cote d'Azur</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="LIPN" corresp="UNIV-PARIS13">Laboratoire d'Informatique de Paris-Nord</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="GALILE" corresp="UNIV-PARIS13">Institut Galilée Université Paris 13</idno>
            <idno type="stamp" n="SORBONNE-PARIS-NORD">Université Sorbonne Paris Nord</idno>
            <idno type="stamp" n="INIST">Institut de l'Information Scientifique et Technique</idno>
            <idno type="stamp" n="UNIV-PARIS">Université Paris Cité</idno>
            <idno type="stamp" n="CONFRENCE-NATIONALE-SUR-LES-APPLICATIONS-PRATIQUES-DE-LINTELLIGENCE-ARTIFICIELLE" corresp="CNRS">Conférence Nationale sur les Applications Pratiques de l’Intelligence Artificielle </idno>
            <idno type="stamp" n="ACT-R" corresp="UNIV-PARIS13">Act'R </idno>
            <idno type="stamp" n="INTERNE-HALCNRS">INTERNE-HALCNRS</idno>
            <idno type="stamp" n="TEST8-HALCNRS">TEST8-HALCNRS</idno>
            <idno type="stamp" n="TEST10-HALCNRS">TEST10-HALCNRS</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">Influence of Pre-annotation on POS-tagged Corpus Development</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Karen</forename>
                    <surname>Fort</surname>
                  </persName>
                  <email type="md5">24fcc09edce5cbf8df003845469f6b01</email>
                  <email type="domain">loria.fr</email>
                  <idno type="idhal" notation="string">karen-fort</idno>
                  <idno type="idhal" notation="numeric">2215</idno>
                  <idno type="halauthorid" notation="string">240168-2215</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-0723-8850</idno>
                  <idno type="IDREF">https://www.idref.fr/176299548</idno>
                  <affiliation ref="#struct-1814"/>
                  <affiliation ref="#struct-994"/>
                </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>
                  <affiliation ref="#struct-54505"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>The Fourth ACL Linguistic Annotation Workshop</title>
                  <date type="start">2010-07-15</date>
                  <date type="end">2010-07-16</date>
                  <settlement>Uppsala</settlement>
                  <country key="SE">Sweden</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">56-63</biblScope>
                  <date type="datePub">2010</date>
                </imprint>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="info.info-tt">Computer Science [cs]/Document and Text Processing</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 article details a series of carefully designed experiments aiming at evaluating the influence of automatic pre-annotation on the manual part-of-speech annotation of a corpus, both from the quality and the time points of view, with a specific attention drawn to biases. For this purpose, we manually annotated parts of the Penn Treebank corpus under various experimental setups, either from scratch or using various pre-annotations. These experiments confirm and detail the gain in quality observed before, while showing that biases do appear and should be taken into account. They finally demonstrate that even a not so accurate tagger can help improving annotation speed.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1814" status="VALID">
          <idno type="IdRef">02802530X</idno>
          <idno type="ISNI">0000000089755987</idno>
          <idno type="RNSR">198822446E</idno>
          <idno type="ROR">https://ror.org/02mn0vt57</idno>
          <idno type="Wikidata">Q3152021</idno>
          <orgName>Institut de l'information scientifique et technique</orgName>
          <orgName type="acronym">INIST</orgName>
          <date type="start">1988-03-15</date>
          <desc>
            <address>
              <addrLine>2, Allée du Parc de Brabois, Rue Jean Zay, 54500 Vandœuvre-lès-Nancy</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inist.fr</ref>
          </desc>
          <listRelation>
            <relation name="UAR76 / UPS76" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-994" status="OLD">
          <orgName>Laboratoire d'Informatique de Paris-Nord</orgName>
          <orgName type="acronym">LIPN</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>Institut Galilée, Université Paris 13, 99 avenue Jean-Baptiste Clément, F-93430, Villetaneuse</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www-lipn.univ-paris13.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-15786" type="direct"/>
            <relation active="#struct-301340" type="direct"/>
            <relation active="#struct-303171" type="direct"/>
            <relation name="UMR7030" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-54505" status="OLD">
          <idno type="RNSR">200818336A</idno>
          <orgName>Analyse Linguistique Profonde à Grande Echelle ; Large-scale deep linguistic processing</orgName>
          <orgName type="acronym">ALPAGE</orgName>
          <date type="end">2016-01-31</date>
          <desc>
            <address>
              <addrLine>Université Paris Diderot, Bât. Olympe de Gouges, case postale 7003, 75205 Paris cedex 13 - INRIA Rocquencourt</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/alpage</ref>
          </desc>
          <listRelation>
            <relation active="#struct-86790" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-300301" 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="institution" xml:id="struct-15786" status="VALID">
          <idno type="ROR">https://ror.org/05f82e368</idno>
          <orgName>Université Paris 13</orgName>
          <orgName type="acronym">UP13</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-paris13.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-301340" status="VALID">
          <orgName>Institut Galilée</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-303171" status="VALID">
          <idno type="IdRef">19077990X</idno>
          <idno type="ROR">https://ror.org/001z21q04</idno>
          <orgName>Université Sorbonne Paris Cité</orgName>
          <orgName type="acronym">USPC</orgName>
          <date type="start">2010-01-01</date>
          <desc>
            <address>
              <addrLine>Université Sorbonne Paris Cité | 100-104, avenue de France | 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sorbonne-paris-cite.fr/fr</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-86790" status="OLD">
          <orgName>Inria Paris-Rocquencourt</orgName>
          <date type="end">2016-03-30</date>
          <desc>
            <address>
              <addrLine>INRIA Rocquencourt : Domaine de Voluceau, Rocquencourt B.P. 105 78153 le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/centre/paris-rocquencourt</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>
      </listOrg>
    </back>
  </text>
</TEI>