<?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-03272825</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="2026-05-16T13:34:34+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">An Evaluation Dataset for Identifying Communicative Functions of Sentences in English Scholarly Papers</title>
            <author role="aut">
              <persName>
                <forename type="first">Kenichi</forename>
                <surname>Iwatsuki</surname>
              </persName>
              <email type="md5">4d8f02fd3d4b71d5e8f90519677da22b</email>
              <email type="domain">nii.ac.jp</email>
              <idno type="idhal" notation="numeric">1103526</idno>
              <idno type="halauthorid" notation="string">2238264-1103526</idno>
              <affiliation ref="#struct-304304"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Florian</forename>
                <surname>Boudin</surname>
              </persName>
              <email type="md5">7f09495b0b68c1f59ad0a09a75b1dbf5</email>
              <email type="domain">univ-nantes.fr</email>
              <idno type="idhal" notation="string">florian-boudin</idno>
              <idno type="idhal" notation="numeric">17314</idno>
              <idno type="halauthorid" notation="string">15328-17314</idno>
              <idno type="IDREF">https://www.idref.fr/130897078</idno>
              <affiliation ref="#struct-473973"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Akiko</forename>
                <surname>Aizawa</surname>
              </persName>
              <email type="md5">624f587b638a2a303122117985d044fe</email>
              <email type="domain">nii.ac.jp</email>
              <idno type="idhal" notation="numeric">863302</idno>
              <idno type="halauthorid" notation="string">2238265-863302</idno>
              <affiliation ref="#struct-304304"/>
              <affiliation ref="#struct-6501"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Florian</forename>
                <surname>Boudin</surname>
              </persName>
              <email type="md5">7f09495b0b68c1f59ad0a09a75b1dbf5</email>
              <email type="domain">univ-nantes.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2021-06-28 16:10:58</date>
              <date type="whenModified">2026-02-02 14:42:04</date>
              <date type="whenReleased">2021-07-02 15:39:14</date>
              <date type="whenProduced">2020-05-11</date>
              <date type="whenEndEmbargoed">2021-06-28</date>
              <ref type="file" target="https://hal.science/hal-03272825v1/document">
                <date notBefore="2021-06-28"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://hal.science/hal-03272825v1/file/2020.lrec-1.212.pdf" id="file-3272825-2875747">
                <date notBefore="2021-06-28"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="22869">
                <persName>
                  <forename>Florian</forename>
                  <surname>Boudin</surname>
                </persName>
                <email type="md5">7f09495b0b68c1f59ad0a09a75b1dbf5</email>
                <email type="domain">univ-nantes.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-03272825</idno>
            <idno type="halUri">https://hal.science/hal-03272825</idno>
            <idno type="halBibtex">iwatsuki:hal-03272825</idno>
            <idno type="halRefHtml">&lt;i&gt;12th Conference on Language Resources and Evaluation (LREC 2020)&lt;/i&gt;, May 2020, Marseille, France</idno>
            <idno type="halRef">12th Conference on Language Resources and Evaluation (LREC 2020), May 2020, Marseille, France</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-3272825-2875747"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNIV-NANTES">Université de Nantes</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="EC-NANTES">Ecole Centrale de Nantes</idno>
            <idno type="stamp" n="UNAM">l'unam - université nantes angers le mans</idno>
            <idno type="stamp" n="LS2N">Laboratoire des Sciences du Numérique de Nantes</idno>
            <idno type="stamp" n="LS2N-TALN" corresp="LS2N">LS2N - équipe TALN ( Traitement Automatique du Langage Naturel )</idno>
            <idno type="stamp" n="INSTITUTS-TELECOM">composantes instituts telecom </idno>
            <idno type="stamp" n="NANTES-UNIVERSITE">Nantes Université</idno>
            <idno type="stamp" n="UNIV-NANTES-AV2022">Université de Nantes</idno>
            <idno type="stamp" n="NU-CENTRALE">École Centrale de Nantes</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">An Evaluation Dataset for Identifying Communicative Functions of Sentences in English Scholarly Papers</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Kenichi</forename>
                    <surname>Iwatsuki</surname>
                  </persName>
                  <email type="md5">4d8f02fd3d4b71d5e8f90519677da22b</email>
                  <email type="domain">nii.ac.jp</email>
                  <idno type="idhal" notation="numeric">1103526</idno>
                  <idno type="halauthorid" notation="string">2238264-1103526</idno>
                  <affiliation ref="#struct-304304"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Florian</forename>
                    <surname>Boudin</surname>
                  </persName>
                  <email type="md5">7f09495b0b68c1f59ad0a09a75b1dbf5</email>
                  <email type="domain">univ-nantes.fr</email>
                  <idno type="idhal" notation="string">florian-boudin</idno>
                  <idno type="idhal" notation="numeric">17314</idno>
                  <idno type="halauthorid" notation="string">15328-17314</idno>
                  <idno type="IDREF">https://www.idref.fr/130897078</idno>
                  <affiliation ref="#struct-473973"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Akiko</forename>
                    <surname>Aizawa</surname>
                  </persName>
                  <email type="md5">624f587b638a2a303122117985d044fe</email>
                  <email type="domain">nii.ac.jp</email>
                  <idno type="idhal" notation="numeric">863302</idno>
                  <idno type="halauthorid" notation="string">2238265-863302</idno>
                  <affiliation ref="#struct-304304"/>
                  <affiliation ref="#struct-6501"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)</title>
                <meeting>
                  <title>12th Conference on Language Resources and Evaluation (LREC 2020)</title>
                  <date type="start">2020-05-11</date>
                  <settlement>Marseille</settlement>
                  <country key="FR">France</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">sentence representation</term>
                <term xml:lang="en">rhetorical structure</term>
                <term xml:lang="en">communicative function</term>
                <term xml:lang="en">formulaic expression</term>
                <term xml:lang="en">multi-word expression</term>
              </keywords>
              <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>Formulaic expressions, such as 'in this paper we propose', are used by authors of scholarly papers to perform communicative functions; the communicative function of the present example is 'stating the aim of the paper'. Collecting such expressions and pairing them with their communicative functions would be highly valuable for various tasks, particularly for writing assistance. However, such collection and paring in a principled and automated manner would require high-quality annotated data, which are not available. In this study, we address this shortcoming by creating a manually annotated dataset for detecting communicative functions in sentences. Starting from a seed list of labelled formulaic expressions, we retrieved new sentences from scholarly papers in the ACL Anthology and asked multiple human evaluators to label communicative functions. To show the usefulness of our dataset, we conducted a series of experiments that determined to what extent sentence representations acquired by recent models, such as word2vec and BERT, can be employed to detect communicative functions in sentences.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="regroupinstitution" xml:id="struct-304304" status="VALID">
          <idno type="IdRef">029909848</idno>
          <idno type="ROR">https://ror.org/057zh3y96</idno>
          <orgName>The University of Tokyo</orgName>
          <orgName type="acronym">UTokyo</orgName>
          <desc>
            <address>
              <addrLine>7 Chome-3-1 Hongo, Bunkyo, Tokyo 113-8654</addrLine>
              <country key="JP"/>
            </address>
            <ref type="url">https://www.u-tokyo.ac.jp/en/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-473973" status="OLD">
          <idno type="IdRef">203637585</idno>
          <idno type="RNSR">201722241F</idno>
          <idno type="ROR">https://ror.org/02snf8m58</idno>
          <orgName>Laboratoire des Sciences du Numérique de Nantes</orgName>
          <orgName type="acronym">LS2N</orgName>
          <date type="start">2017-01-01</date>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>Université de Nantes – faculté des Sciences et Techniques (FST)2 Chemin de la HoussinièreBP 92208, 44322 Nantes Cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.ls2n.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-97058" type="direct"/>
            <relation active="#struct-93263" type="indirect"/>
            <relation active="#struct-111023" type="direct"/>
            <relation name="UMR6004" active="#struct-441569" type="direct"/>
            <relation active="#struct-481355" type="direct"/>
            <relation active="#struct-302102" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-6501" status="VALID">
          <idno type="ROR">https://ror.org/04ksd4g47</idno>
          <orgName>National Institute of Informatics</orgName>
          <orgName type="acronym">NII</orgName>
          <desc>
            <address>
              <addrLine>2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430</addrLine>
              <country key="JP"/>
            </address>
            <ref type="url">http://www.nii.ac.jp/en/</ref>
          </desc>
        </org>
        <org type="regrouplaboratory" xml:id="struct-97058" status="OLD">
          <orgName>Université de Nantes - UFR des Sciences et des Techniques</orgName>
          <orgName type="acronym">UN UFR ST</orgName>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>2, rue de la Houssinière - BP 92208 - 44322 Nantes cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.sciences-techniques.univ-nantes.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-93263" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-93263" status="OLD">
          <idno type="IdRef">026403447</idno>
          <idno type="ROR">https://ror.org/03gnr7b55</idno>
          <orgName>Université de Nantes</orgName>
          <orgName type="acronym">UN</orgName>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>1, quai de Tourville - BP 13522 - 44035 Nantes cedex 1</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-nantes.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-111023" status="OLD">
          <idno type="IdRef">03063525X</idno>
          <idno type="ISNI">0000000122039289</idno>
          <idno type="ROR">https://ror.org/03nh7d505</idno>
          <orgName>École Centrale de Nantes</orgName>
          <orgName type="acronym">ECN</orgName>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>1 rue de la Noë - BP 92101 - 44321 Nantes cedex 3</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ec-nantes.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>
        <org type="institution" xml:id="struct-481355" status="VALID">
          <idno type="IdRef">202743233</idno>
          <idno type="ROR">https://ror.org/030hj3061</idno>
          <orgName>IMT Atlantique</orgName>
          <orgName type="acronym">IMT Atlantique</orgName>
          <date type="start">2017-01-01</date>
          <desc>
            <address>
              <addrLine>Campus Brest : Technopôle Brest-Iroise CS 8381829238 BREST Cedex 3 -Campus Nantes : 4, rue Alfred Kastler- La chantrerie 44300 NANTES -Campus Rennes :  2 Rue de la Châtaigneraie, 35510 CESSON SEVIGNE</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.imt-atlantique.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302102" type="direct"/>
          </listRelation>
        </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>
    </back>
  </text>
</TEI>