<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta />
    <article-meta>
      <title-group>
        <article-title>An Overview of Terminological Resources available for French bioNLP</article-title>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <string-name>Aurelie Neveol</string-name>
          <xref ref-type="aff" rid="aff2">2</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Dietrich Rebholz-Schuhmann</string-name>
          <xref ref-type="aff" rid="aff0">0</xref>
          <xref ref-type="aff" rid="aff1">1</xref>
        </contrib>
        <contrib contrib-type="author">
          <string-name>Pierre Zweigenbaum</string-name>
          <xref ref-type="aff" rid="aff2">2</xref>
        </contrib>
        <aff id="aff0">
          <label>0</label>
          <institution>EBI</institution>
          ,
          <addr-line>Hinxton, Cambridgeshire, CB10 1SD</addr-line>
          ,
          <country country="UK">United Kingdom</country>
        </aff>
        <aff id="aff1">
          <label>1</label>
          <institution>ICL, University of Zurich</institution>
          ,
          <addr-line>8050 Zurich</addr-line>
          ,
          <country country="CH">Switzerland</country>
        </aff>
        <aff id="aff2">
          <label>2</label>
          <institution>LIMSI-CNRS UPR 3251</institution>
          ,
          <addr-line>Rue John von Neumann, 91400 Orsay</addr-line>
          ,
          <country country="FR">France</country>
        </aff>
      </contrib-group>
      <abstract>
        <p>Terminological resources in languages other than English are playing a critical role in all kinds of medical administrative solutions in countries where English is not an o cial language, or not the only o cial language. French bene ts from being among the top ve most covered languages in the UMLS in number of concepts. Herein, we review the extent of this coverage as well as the sources and methods for additional material available for French.</p>
      </abstract>
      <kwd-group>
        <kwd>France</kwd>
        <kwd>Natural Language Processing</kwd>
        <kwd>Translating</kwd>
        <kwd>Terminology as topic/methods</kwd>
      </kwd-group>
    </article-meta>
  </front>
  <body>
    <sec id="sec-1">
      <title>Introduction</title>
      <p>2.1</p>
    </sec>
    <sec id="sec-2">
      <title>Material and methods</title>
      <sec id="sec-2-1">
        <title>Currently available resources</title>
        <p>The UMLS R (Uni ed Medical Language System R ; Bodenreider 2004) is a
major terminological resource for many languages, including French. The UMLS
Metathesaurus R is the structured union of existing biomedical vocabularies,
some of which include terms in languages other than English. The second row of</p>
        <p>Table 1 provides an overview of the various sources in the UMLS Metathesaurus
(version 2012AA) with an indication of size using the number of unique strings
and Concept Unique Identi ers (CUIs) covered4. As far as French is concerned,
the MeSH R thesaurus (Medical Subject Headings) and the Medical Dictionary
for Regulatory Activities (MedDRA) make the bulk of the French terms available
in the UMLS.</p>
        <p>Rows 3 to 5 in Table 1 show some of the other terminologies available through
the UMLS for English that are also available in French but not included in
the UMLS release. It should be noted that some light processing is required
to map the French terms (strings) from these resources to UMLS CUIs as the
data is provided natively for each terminology, i.e. each term is mapped to a
terminology unique identi er which is also present in the UMLS Metathesaurus.
Using the English version of the UMLS, the mappings between these identi ers
and UMLS CUIs can be recovered: for instance, the French term \bras robotique"
in SNOMED v3.5 has code A-01100 which is found in the Metathesaurus with
CUI C0336542 and preferred English term \Robotic arm". Therefore, it can
be inferred that the French term \bras robotique" should be assigned to CUI
C0336542.</p>
        <p>Other resources in French have not been mapped to the UMLS. The European
Health Terminology Ontology Portal (EHTOP5) provides an integrated access
to four of them: CCAM, ATC, Orphanet, and CISMeF. CCAM (Classi cation
4 This number was obtained using the following SQL query:
select LAT, count(distinct STR collate utf8 bin) from MRCONSO where
LAT="FRE"; and similarly for the CUIs.
5 http://www.ehtop.eu/
Commune des Actes Medicaux) is a French counterpart of CPT (Current
Procedural Terminology). The Anatomical Therapeutic Chemical (ATC) classi cation
system is a drug classi cation system managed by the World Health
Organization (WHO); its counterpart in the UMLS is RXNORM, which is developed by
the US National Library of Medicine. Orphanet is a portal of information on
rare diseases which has driven the development of a terminology which, in turn,
led to the OntoOrpha ontology. CISMeF (Catalogue et Index des Sites Medicaux
Francophone; Darmoni et al. 2000) is an online portal providing health
information in French relying on MeSH indexing of online documents. The so-called
CISMeF terminology comprises MeSH as well as additional resources in French:
additional Entry Terms, additional resources types, and metaterms, which are
broad categories corresponding to medical specialties. CISMeF metaterms
comprise links to relevant MeSH terms, allowing for specialty-oriented document
searches and specialty pro ling of corpora. Finally, we can also mention the
case of the Foundational Model of Anatomy (FMA). The English version of this
ontology is part of the UMLS and is also included in ETHOP. In addition to
English, a handful of other languages are partially covered, including French:
4,452 concepts out of 82,083 (5.4%) have at least one term in French.</p>
        <p>
          Then, the issue of string normalization and pre-processing for use in
Natural Language Processing applications remains to be addressed. Many of the
strategies used for English are also applicable for French [
          <xref ref-type="bibr" rid="ref14 ref9">9, 14</xref>
          ].
        </p>
        <p>
          Over the past decade, there has been a collaborative e ort to develop a French
\Specialist Lexicon" comprising linguistic information about in ected forms and
lemmas found in biomedical terms [
          <xref ref-type="bibr" rid="ref15 ref3">15, 3</xref>
          ]. Table 2 shows details of the UMLF
(Uni ed Medical Language for French) contents.
        </p>
      </sec>
      <sec id="sec-2-2">
        <title>Contributors</title>
        <p>Contributions to the resources described above came from many researchers
throughout Canada, France, and Switzerland. These e orts came from
institutional initiatives or from the concerted work of individual researchers.</p>
        <p>
          INSERM has been a partner of the National Library of Medicine since 1969.
They have been producing a version of MeSH translated into French every year
since 1986. While all main headings were available in French, only selected
Entry Terms are also translated. To address the need for additional Entry Terms
in French, INIST has helped INSERM with the manual translation of several
thousand terms. Meanwhile, the CISMeF team has been enhancing the MeSH
resources available in French by adding synonyms [
          <xref ref-type="bibr" rid="ref7">7</xref>
          ] and researching methods
for automatically translating Entry terms from English into French ([
          <xref ref-type="bibr" rid="ref11 ref13 ref6">11, 13, 6</xref>
          ].
Other e orts towards building an automatic tool for MeSH indexing also resulted
in the development of MeSH terminological resources [
          <xref ref-type="bibr" rid="ref12">12</xref>
          ].
        </p>
        <p>
          The French version of SNOMED is the results of the e orts of Dr. R.A. C^ote
[
          <xref ref-type="bibr" rid="ref4">4</xref>
          ] in the development of SMOMED v3.5 (also known as SNOMED
International). It has been used together with other resources to explore methods for
obtaining a French version of SNOMED CT [
          <xref ref-type="bibr" rid="ref1">1</xref>
          ]. This work was part of a larger
e ort to develop a portal integrating medical terminologies in French and other
European languages [
          <xref ref-type="bibr" rid="ref8">8</xref>
          ]: the above mentioned EHTOP portal.
        </p>
        <p>
          Several nationally-funded projects contributed to the extension of these
resources. Beyond the already cited UMLF project, let us mention VUMeF [
          <xref ref-type="bibr" rid="ref5">5</xref>
          ]
and then InterSTIS (http://www.interstis.org/) which helped in the French
translation of MeSH and SNOMED.
3
3.1
        </p>
      </sec>
    </sec>
    <sec id="sec-3">
      <title>Discussion</title>
      <sec id="sec-3-1">
        <title>Needs</title>
        <p>We identify three important needs for enhancing the existing resources for French,
in order of increasing di culty:</p>
      </sec>
      <sec id="sec-3-2">
        <title>1. integrate available resources into UMLS in order to facilitate their</title>
        <p>access and use: for instance, French versions of ICD10, FMA, SNOMED;</p>
      </sec>
      <sec id="sec-3-3">
        <title>2. enhance the content of resources currently integrated in the UMLS</title>
        <p>with the result of work that has been on-going for the past decade, e.g.</p>
        <p>
          UMLF, MeSH terminological resources for indexing;
3. have the UMLS cover terminologies that are used in clinical
practice in countries where French is an o cial language used in hospitals
(France, Canada, Belgium, Switzerland, French-speaking African countries,
etc.). For instance, as mentioned above, terminologies such as CCAM are
not part of the UMLS. [
          <xref ref-type="bibr" rid="ref10 ref2">10, 2</xref>
          ] recently proposed semi-automated methods to
map CCAM terms to UMLS CUIs. However, there is a need for
terminology developers to o cially validate the results of the automatic mappings
and promote/authorize the distribution of the nal resource. Besides, the
composed nature of CCAM terms makes them very speci c, which entails a
limited exact correspondence to procedures de ned in other medical
vocabularies and a need to create new concepts in the UMLS Metathesaurus.
3.2
        </p>
      </sec>
      <sec id="sec-3-4">
        <title>Barriers</title>
        <p>We consider that the main barriers to further progress are the following:
1. lack of a concerted e ort: while the NLM is prioritizing the development
of resources in English, some resources for other languages are developed for a
particular application and the means (time, funds) to produce a distributable
version are not available. A roadmap for further developments is needed,
listing aims and objectives, and methods to obtain appropriate support from
relevant teams and organizations. A project such as MANTRA could
provide a venue for preparing such a concerted e ort. Additionally, societies
such as IMIA could provide a longer-term framework for such an initiative.
For instance, its recently created Francophone SIG intends to address the
promotion of work on French-language corpora and controlled vocabularies.
Coordinated action in di erent languages could build on language-speci c
actions.
2. licensing issues: the access to some terminologies is restricted (SNOMED
CT, ATC, CISMeF, . . . ); terminologies underpin the development of science,
standards and information systems and should be made widely available at
no cost.
4</p>
      </sec>
    </sec>
    <sec id="sec-4">
      <title>Conclusion</title>
      <p>This overview of French resources for the biomedical domain shows that there is
a real interest from the community for using these resources, as well as e orts to
create quality resources. However, there is an on-going need for encouraging the
sharing of the end-results under the umbrella of a standard framework such as
the UMLS. Funded projects are a possible means for this type of activity (see,
e.g., UMLF, VUMeF, InterSTIS, EHTOP, MANTRA); societies (e.g., IMIA) are
another framework where it could be coordinated.</p>
    </sec>
    <sec id="sec-5">
      <title>Acknowledgements</title>
      <p>The authors acknowledge travel funding from the EU STREP project grant
296410 (\Mantra") under the 7th EU Framework Programme within Theme
\Intelligent Content and Semantics", \Challenge 4: Technologies for Digital Content
and Languages" (ICT 2011.4.1).</p>
    </sec>
  </body>
  <back>
    <ref-list>
      <ref id="ref1">
        <mixed-citation>
          1.
          <string-name>
            <surname>Abdoune</surname>
            ,
            <given-names>H.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Merabti</surname>
            ,
            <given-names>T.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Darmoni</surname>
            ,
            <given-names>S.J.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Joubert</surname>
            ,
            <given-names>M.</given-names>
          </string-name>
          :
          <article-title>Assisting the translation of the CORE subset of SNOMED CT into French</article-title>
          . In: Moen,
          <string-name>
            <given-names>A.</given-names>
            ,
            <surname>Andersen</surname>
          </string-name>
          ,
          <string-name>
            <given-names>S.K.</given-names>
            ,
            <surname>Aarts</surname>
          </string-name>
          ,
          <string-name>
            <given-names>J.</given-names>
            ,
            <surname>Hurlen</surname>
          </string-name>
          , P. (eds.) MIE.
          <article-title>Studies in Health Technology and Informatics</article-title>
          , vol.
          <volume>169</volume>
          , pp.
          <volume>819</volume>
          {
          <fpage>823</fpage>
          . IOS Press (
          <year>2011</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref2">
        <mixed-citation>
          2.
          <string-name>
            <surname>Bousquet</surname>
            ,
            <given-names>C.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Souvignet</surname>
            ,
            <given-names>J.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Merabti</surname>
            ,
            <given-names>T.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Sadou</surname>
            ,
            <given-names>E.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Trombert</surname>
            ,
            <given-names>B.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Rodrigues</surname>
            ,
            <given-names>J.M.</given-names>
          </string-name>
          :
          <article-title>Method for mapping the French CCAM terminology to the UMLS metathesaurus</article-title>
          . In: Mantas,
          <string-name>
            <given-names>J.</given-names>
            ,
            <surname>Andersen</surname>
          </string-name>
          ,
          <string-name>
            <given-names>S.K.</given-names>
            ,
            <surname>Mazzoleni</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M.C.</given-names>
            ,
            <surname>Blobel</surname>
          </string-name>
          ,
          <string-name>
            <given-names>B.</given-names>
            ,
            <surname>Quaglini</surname>
          </string-name>
          ,
          <string-name>
            <given-names>S.</given-names>
            ,
            <surname>Moen</surname>
          </string-name>
          ,
          <string-name>
            <surname>A</surname>
          </string-name>
          . (eds.)
          <article-title>Stud Health Technol Inform</article-title>
          .
          <source>Studies in Health Technology and Informatics</source>
          , vol.
          <volume>180</volume>
          , pp.
          <volume>164</volume>
          {
          <fpage>168</fpage>
          . IOS Press (
          <year>2012</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref3">
        <mixed-citation>
          3.
          <string-name>
            <surname>Cartoni</surname>
            ,
            <given-names>B.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Zweigenbaum</surname>
            ,
            <given-names>P.</given-names>
          </string-name>
          :
          <article-title>Extension of a specialised lexicon using speci c terminological data: the Uni ed Medical Lexicon for French (UMLF)</article-title>
          .
          <source>In: Proc. EURALEX</source>
          (
          <year>2010</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref4">
        <mixed-citation>
          4. Co^te,
          <string-name>
            <given-names>R.A.</given-names>
            ,
            <surname>Brochu</surname>
          </string-name>
          ,
          <string-name>
            <given-names>L.</given-names>
            ,
            <surname>Cabana</surname>
          </string-name>
          ,
          <string-name>
            <surname>L.</surname>
          </string-name>
          : SNOMED Internationale {
          <article-title>Repertoire d'anatomie pathologique</article-title>
          . Secretariat francophone international de nomenclature medicale, Sherbrooke, Quebec (
          <year>1997</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref5">
        <mixed-citation>
          5.
          <string-name>
            <surname>Darmoni</surname>
            ,
            <given-names>S.J.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Jarrousse</surname>
            ,
            <given-names>E.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Zweigenbaum</surname>
            ,
            <given-names>P.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Le</surname>
            <given-names>Beux</given-names>
          </string-name>
          ,
          <string-name>
            <given-names>P.</given-names>
            ,
            <surname>Namer</surname>
          </string-name>
          ,
          <string-name>
            <given-names>F.</given-names>
            ,
            <surname>Baud</surname>
          </string-name>
          ,
          <string-name>
            <given-names>R.</given-names>
            ,
            <surname>Joubert</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M.</given-names>
            ,
            <surname>Vallee</surname>
          </string-name>
          ,
          <string-name>
            <surname>H.</surname>
          </string-name>
          , Co^te,
          <string-name>
            <given-names>R.A.</given-names>
            ,
            <surname>Buemi</surname>
          </string-name>
          ,
          <string-name>
            <given-names>A.</given-names>
            ,
            <surname>Bourigault</surname>
          </string-name>
          ,
          <string-name>
            <given-names>D.</given-names>
            ,
            <surname>Recource</surname>
          </string-name>
          ,
          <string-name>
            <given-names>G.</given-names>
            ,
            <surname>Jeanneau</surname>
          </string-name>
          ,
          <string-name>
            <given-names>S.</given-names>
            ,
            <surname>Rodrigues</surname>
          </string-name>
          ,
          <string-name>
            <surname>J.M.:</surname>
          </string-name>
          <article-title>VUMeF: Extending the French involvement in the UMLS Metathesaurus</article-title>
          .
          <source>In: Proc. AMIA Symp</source>
          . p.
          <volume>824</volume>
          (
          <year>2003</year>
          ),
          <article-title>(poster)</article-title>
        </mixed-citation>
      </ref>
      <ref id="ref6">
        <mixed-citation>
          6.
          <string-name>
            <surname>Deleger</surname>
            ,
            <given-names>L.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Merabti</surname>
            ,
            <given-names>T.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Lecrocq</surname>
            ,
            <given-names>T.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Joubert</surname>
            ,
            <given-names>M.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Zweigenbaum</surname>
            ,
            <given-names>P.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Darmoni</surname>
            ,
            <given-names>S.J.:</given-names>
          </string-name>
          <article-title>A twofold strategy for translating a medical terminology into French</article-title>
          .
          <source>In: Proc AMIA Symp</source>
          . pp.
          <volume>152</volume>
          {
          <issue>156</issue>
          (
          <year>2010</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref7">
        <mixed-citation>
          7.
          <string-name>
            <surname>Douyere</surname>
            ,
            <given-names>M.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Soualmia</surname>
            ,
            <given-names>L.F.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Neveol</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Rogozan</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Dahamna</surname>
            ,
            <given-names>B.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Leroy</surname>
            ,
            <given-names>J.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Thirion</surname>
            ,
            <given-names>B.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Darmoni</surname>
            ,
            <given-names>S.J.:</given-names>
          </string-name>
          <article-title>Enhancing the MeSH thesaurus to retrieve French online health resources in a quality-controlled gateway</article-title>
          .
          <source>Health Information and Libraries Journal</source>
          (
          <year>2004</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref8">
        <mixed-citation>
          8.
          <string-name>
            <surname>Grosjean</surname>
            ,
            <given-names>J.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Merabti</surname>
            ,
            <given-names>T.</given-names>
          </string-name>
          , Gri on, N.,
          <string-name>
            <surname>Dahamna</surname>
            ,
            <given-names>B.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Darmoni</surname>
            ,
            <given-names>S.J.:</given-names>
          </string-name>
          <article-title>Multiterminology cross-lingual model to create the European Health Terminology/Ontology Portal</article-title>
          .
          <source>In: Proc. 9th international conference on Terminology and Arti cal Intelligence</source>
          . pp.
          <volume>119</volume>
          {
          <issue>122</issue>
          (
          <year>2011</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref9">
        <mixed-citation>
          9.
          <string-name>
            <surname>Hettne</surname>
          </string-name>
          , K.M.,
          <string-name>
            <surname>van Mulligen</surname>
            ,
            <given-names>E.M.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Schuemie</surname>
            ,
            <given-names>M.J.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Schijvenaars</surname>
            ,
            <given-names>B.J.A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Kors</surname>
            ,
            <given-names>J.A.</given-names>
          </string-name>
          :
          <article-title>Rewriting and suppressing UMLS terms for improved biomedical term identi cation</article-title>
          .
          <source>J. Biomedical Semantics</source>
          <volume>1</volume>
          ,
          <issue>5</issue>
          (
          <year>2010</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref10">
        <mixed-citation>
          10.
          <string-name>
            <surname>Merabti</surname>
            ,
            <given-names>T.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Massari</surname>
            ,
            <given-names>P.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Joubert</surname>
            ,
            <given-names>M.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Sadou</surname>
            ,
            <given-names>E.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Lecroq</surname>
            ,
            <given-names>T.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Abdoune</surname>
            ,
            <given-names>H.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Rodrigues</surname>
            ,
            <given-names>J.M.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Darmoni</surname>
            ,
            <given-names>S.J.:</given-names>
          </string-name>
          <article-title>An automated approach to map a French terminology to UMLS</article-title>
          .
          <source>Stud Health Technol Inform 1040{4(Pt 2)</source>
          ,
          <volume>5</volume>
          (
          <year>2010</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref11">
        <mixed-citation>
          11.
          <string-name>
            <surname>Neveol</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Ozdowska</surname>
            ,
            <given-names>S.</given-names>
          </string-name>
          :
          <article-title>Extraction bilingue de termes medicaux dans un corpus parallele anglais/francais</article-title>
          . In: Pinson,
          <string-name>
            <given-names>S.</given-names>
            ,
            <surname>Vincent</surname>
          </string-name>
          , N. (eds.) EGC. Revue des Nouvelles Technologies de l'Information, vol.
          <source>RNTI-E-3</source>
          , pp.
          <volume>655</volume>
          {
          <fpage>666</fpage>
          .
          <string-name>
            <surname>CepaduesEditions</surname>
          </string-name>
          (
          <year>2005</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref12">
        <mixed-citation>
          12.
          <string-name>
            <surname>Neveol</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Douyere</surname>
            ,
            <given-names>M.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Rogozan</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Darmoni</surname>
            ,
            <given-names>S.J.</given-names>
          </string-name>
          :
          <article-title>Construction de ressources terminologiques en sante pour un systeme d'indexation automatique</article-title>
          .
          <source>In: Proc. Journees INTEX/NOOJ</source>
          . Tours, France (
          <year>2004</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref13">
        <mixed-citation>
          13.
          <string-name>
            <surname>Ozdowska</surname>
            ,
            <given-names>S.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Neveol</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Thirion</surname>
            ,
            <given-names>B.</given-names>
          </string-name>
          :
          <article-title>Traduction compositionnelle automatique de bitermes dans des corpus anglais/francais alignes</article-title>
          .
          <source>In: Proc. 6th international conference on Terminology and Arti cal Intelligence</source>
          . pp.
          <volume>83</volume>
          {
          <issue>84</issue>
          (
          <year>2005</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref14">
        <mixed-citation>
          14.
          <string-name>
            <surname>Wu</surname>
            ,
            <given-names>S.T.I.</given-names>
          </string-name>
          , Liu,
          <string-name>
            <given-names>H.</given-names>
            ,
            <surname>Li</surname>
          </string-name>
          ,
          <string-name>
            <given-names>D.</given-names>
            ,
            <surname>Tao</surname>
          </string-name>
          ,
          <string-name>
            <given-names>C.</given-names>
            ,
            <surname>Musen</surname>
          </string-name>
          ,
          <string-name>
            <given-names>M.A.</given-names>
            ,
            <surname>Chute</surname>
          </string-name>
          ,
          <string-name>
            <given-names>C.G.</given-names>
            ,
            <surname>Shah</surname>
          </string-name>
          ,
          <string-name>
            <surname>N.H.</surname>
          </string-name>
          :
          <article-title>Uni ed Medical Language System term occurrences in clinical notes: a large-scale corpus analysis</article-title>
          .
          <source>JAMIA</source>
          <volume>19</volume>
          (
          <year>e1</year>
          ) (
          <year>2012</year>
          )
        </mixed-citation>
      </ref>
      <ref id="ref15">
        <mixed-citation>
          15.
          <string-name>
            <surname>Zweigenbaum</surname>
            ,
            <given-names>P.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Baud</surname>
            ,
            <given-names>R.H.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Burgun</surname>
            ,
            <given-names>A.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Namer</surname>
            ,
            <given-names>F.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Jarrousse</surname>
            ,
            <given-names>E.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Grabar</surname>
            ,
            <given-names>N.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Ruch</surname>
            ,
            <given-names>P.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Le Du</surname>
            ,
            <given-names>F.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Forget</surname>
            ,
            <given-names>J.F.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Douyere</surname>
            ,
            <given-names>M.</given-names>
          </string-name>
          ,
          <string-name>
            <surname>Darmoni</surname>
            ,
            <given-names>S.:</given-names>
          </string-name>
          <article-title>A uni ed medical lexicon for French</article-title>
          .
          <source>International Journal of Medical Informatics</source>
          <volume>74</volume>
          (
          <issue>2</issue>
          {4),
          <volume>119</volume>
          {124 (Mar
          <year>2005</year>
          ), http://dx.doi.org/10.1016/j.ijmedinf.
          <year>2004</year>
          .
          <volume>03</volume>
          .010
        </mixed-citation>
      </ref>
    </ref-list>
  </back>
</article>