<?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-01711331</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="2026-05-19T22:11:16+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Comparative study of Named-Entity Recognition methods in the agronomical domain</title>
            <author role="aut">
              <persName>
                <forename type="first">Huy</forename>
                <surname>Do</surname>
              </persName>
              <idno type="idhal" notation="numeric">786136</idno>
              <idno type="halauthorid" notation="string">1315247-786136</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-2588-2858</idno>
              <affiliation ref="#struct-409780"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Hanh</forename>
                <surname>Tran</surname>
              </persName>
              <idno type="idhal" notation="numeric">768425</idno>
              <idno type="halauthorid" notation="string">707994-768425</idno>
              <idno type="IDREF">https://www.idref.fr/168557401</idno>
              <affiliation ref="#struct-409780"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Quang</forename>
                <surname>Khoat Than</surname>
              </persName>
              <idno type="halauthorid">1315248-0</idno>
              <affiliation ref="#struct-321656"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Pierre</forename>
                <surname>Larmande</surname>
              </persName>
              <email type="md5">6d283935a9e7ff904cb0805a0cf2811b</email>
              <email type="domain">ird.fr</email>
              <idno type="idhal" notation="string">pierre-larmande</idno>
              <idno type="idhal" notation="numeric">753219</idno>
              <idno type="halauthorid" notation="string">27384-753219</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/F-2144-2016</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2923-9790</idno>
              <idno type="IDREF">https://www.idref.fr/122767802</idno>
              <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/F-2144-2016</idno>
              <affiliation ref="#struct-213159"/>
              <affiliation ref="#struct-67872"/>
              <affiliation ref="#struct-409780"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Pierre</forename>
                <surname>Larmande</surname>
              </persName>
              <email type="md5">6d283935a9e7ff904cb0805a0cf2811b</email>
              <email type="domain">ird.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2018-02-17 11:44:01</date>
              <date type="whenModified">2025-05-12 15:06:08</date>
              <date type="whenReleased">2018-02-23 15:14:23</date>
              <date type="whenProduced">2018-03-18</date>
              <date type="whenEndEmbargoed">2018-02-17</date>
              <ref type="file" target="https://hal.science/hal-01711331v1/document">
                <date notBefore="2018-02-17"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-01711331v1/file/comparative-study-named-2018.pdf" id="file-1711331-1752011">
                <date notBefore="2018-02-17"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="115093">
                <persName>
                  <forename>Pierre</forename>
                  <surname>Larmande</surname>
                </persName>
                <email type="md5">6d283935a9e7ff904cb0805a0cf2811b</email>
                <email type="domain">ird.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-01711331</idno>
            <idno type="halUri">https://hal.science/hal-01711331</idno>
            <idno type="halBibtex">do:hal-01711331</idno>
            <idno type="halRefHtml">&lt;i&gt;CiCling&lt;/i&gt;, Mar 2018, Hanoi, Vietnam</idno>
            <idno type="halRef">CiCling, Mar 2018, Hanoi, Vietnam</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-1711331-1752011"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="IRD">IRD - Institut de recherche pour le développement</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="INRA">INRA - Institut national de la recherche agronomique</idno>
            <idno type="stamp" n="AGREENIUM">Archive ouverte en agrobiosciences</idno>
            <idno type="stamp" n="UNIV-MONTPELLIER">Université de Montpellier</idno>
            <idno type="stamp" n="INRAE">Institut National de Recherche en Agriculture, Alimentation et Environnement</idno>
            <idno type="stamp" n="UM-2015-2021" corresp="UNIV-MONTPELLIER">Université de Montpellier (2015-2021)</idno>
            <idno type="stamp" n="IA">Intelligence Artificielle</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="0">No</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Comparative study of Named-Entity Recognition methods in the agronomical domain</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Huy</forename>
                    <surname>Do</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">786136</idno>
                  <idno type="halauthorid" notation="string">1315247-786136</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-2588-2858</idno>
                  <affiliation ref="#struct-409780"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Hanh</forename>
                    <surname>Tran</surname>
                  </persName>
                  <idno type="idhal" notation="numeric">768425</idno>
                  <idno type="halauthorid" notation="string">707994-768425</idno>
                  <idno type="IDREF">https://www.idref.fr/168557401</idno>
                  <affiliation ref="#struct-409780"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Quang</forename>
                    <surname>Khoat Than</surname>
                  </persName>
                  <idno type="halauthorid">1315248-0</idno>
                  <affiliation ref="#struct-321656"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Pierre</forename>
                    <surname>Larmande</surname>
                  </persName>
                  <email type="md5">6d283935a9e7ff904cb0805a0cf2811b</email>
                  <email type="domain">ird.fr</email>
                  <idno type="idhal" notation="string">pierre-larmande</idno>
                  <idno type="idhal" notation="numeric">753219</idno>
                  <idno type="halauthorid" notation="string">27384-753219</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/F-2144-2016</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2923-9790</idno>
                  <idno type="IDREF">https://www.idref.fr/122767802</idno>
                  <idno type="RESEARCHERID">http://www.researcherid.com/rid/http://www.researcherid.com/rid/F-2144-2016</idno>
                  <affiliation ref="#struct-213159"/>
                  <affiliation ref="#struct-67872"/>
                  <affiliation ref="#struct-409780"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>CiCling</title>
                  <date type="start">2018-03-18</date>
                  <settlement>Hanoi</settlement>
                  <country key="VN">Vietnam</country>
                </meeting>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Plant Genomics</term>
                <term xml:lang="en">Bioinformatics</term>
                <term xml:lang="en">NER</term>
                <term xml:lang="en">LSTM-CRF</term>
                <term xml:lang="en">Text mining</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-bi">Computer Science [cs]/Bioinformatics [q-bio.QM]</classCode>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-ne">Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]</classCode>
              <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>Text mining is becoming an important part of research topic in biology with the original purpose to extract biological entities such as genes, proteins and traits to extend the knowledge from scientific papers. However, few thorough studies on text mining and applications are developed for plant molecular biology data, especially rice, thus resulting a lack of datasets available to train models. Since there is no/rare benchmark for rice, we have to face various difficulties in exploiting advanced machine learning methods for accurate analysis of rice bibliography. In this article, we developed a new training datasets (Oryzabase) as the benchmark. Then, we evaluated the performance of several current approaches to find a methodology with the best results and assigned it as the state of the art method for our own technique in the future. We applied Name Entities Recognition (NER) tagger, which is built from a Long Short Term Memory model, and combined with Conditional Random Fields (LSTM-CRF) to extract information of plant genes and proteins. We analyzed the performance of LSTM-CRF when applying to the Oryzabase dataset and improved the results up to 89% in F1. We found that on average, the result from LSTM-CRF is more exploitable with the new benchmark.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-409780" status="VALID">
          <idno type="ROR">https://ror.org/04nyv3z04</idno>
          <orgName>University of Science and Technology of Hanoi</orgName>
          <orgName type="acronym">USTH</orgName>
          <date type="start">2009-01-01</date>
          <desc>
            <address>
              <addrLine>A21 Building, Vietnam Academy of Science and Technology, 18 Hoang Quoc Viet, Cau Giay, Ha Noi</addrLine>
              <country key="VN"/>
            </address>
            <ref type="url">https://www.usth.edu.vn/en/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-321656" status="VALID">
          <idno type="ROR">https://ror.org/04nyv3z04</idno>
          <orgName>Hanoi University of Science and Technology</orgName>
          <orgName type="acronym">HUST</orgName>
          <date type="start">1956-01-01</date>
          <desc>
            <address>
              <addrLine>Institut polytechnique de Hanoi, 1 Dai Co Viet Road, Ha Noi</addrLine>
              <country key="VN"/>
            </address>
            <ref type="url">https://en.hust.edu.vn/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-213159" status="OLD">
          <orgName>Institut de Biologie Computationnelle</orgName>
          <orgName type="acronym">IBC</orgName>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <addrLine>95 rue de la Galéra, 34095 Montpellier</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ibc-montpellier.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-92114" type="direct"/>
            <relation active="#struct-300009" type="direct"/>
            <relation active="#struct-410122" type="direct"/>
            <relation active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-67872" status="VALID">
          <idno type="IdRef">050165224</idno>
          <idno type="ROR">https://ror.org/05q3vnk25</idno>
          <orgName>Institut de Recherche pour le Développement</orgName>
          <orgName type="acronym">IRD</orgName>
          <desc>
            <address>
              <addrLine>SiègeLe Sextant 44, bd de DunkerqueCS 9000913572 Marseille cedex 02</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ird.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-92114" status="OLD">
          <idno type="ROR">https://ror.org/01x3gbx83</idno>
          <orgName>Institut National de la Recherche Agronomique</orgName>
          <orgName type="acronym">INRA</orgName>
          <date type="start">1946-05-18</date>
          <date type="end">2019-12-31</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inra.fr</ref>
          </desc>
        </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-410122" status="OLD">
          <idno type="ISNI">0000000120970141</idno>
          <idno type="ROR">https://ror.org/051escj72</idno>
          <orgName>Université de Montpellier</orgName>
          <orgName type="acronym">UM</orgName>
          <date type="end">2021-12-31</date>
          <desc>
            <address>
              <addrLine>163 rue Auguste Broussonnet - 34090 Montpellier</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.umontpellier.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>
    </back>
  </text>
</TEI>