Conference paper Open Access

Leveraging Linguistic Linked Data for Cross-Lingual Model Transfer in the Pharmaceutical Domain

Jorge Gracia; Christian Fäth; Matthias Hartung; Max Ionov; Julia Bosque-Gil; Susana Veríssimo; Christian Chiarcos; Matthias Orlikowski


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="653" ind1=" " ind2=" ">
    <subfield code="a">Apertium RDF, cross-lingual model transfer, Fintan</subfield>
  </datafield>
  <controlfield tag="005">20201215132816.0</controlfield>
  <controlfield tag="001">4322607</controlfield>
  <datafield tag="711" ind1=" " ind2=" ">
    <subfield code="d">2-6 November  2020</subfield>
    <subfield code="g">ISWC 2020</subfield>
    <subfield code="a">19th International Semantic Web Conference</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Goethe University Frankfurt</subfield>
    <subfield code="a">Christian Fäth</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Semalytix GmbH</subfield>
    <subfield code="a">Matthias Hartung</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Goethe University Frankfurt</subfield>
    <subfield code="a">Max Ionov</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Zaragoza</subfield>
    <subfield code="a">Julia Bosque-Gil</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Semalytix GmbH</subfield>
    <subfield code="a">Susana Veríssimo</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Goethe University Frankfurt</subfield>
    <subfield code="a">Christian Chiarcos</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Semalytix GmbH</subfield>
    <subfield code="a">Matthias Orlikowski</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">721008</subfield>
    <subfield code="z">md5:24c25cc5c94b00ccd86c05fb1e0b40d3</subfield>
    <subfield code="u">https://zenodo.org/record/4322607/files/PaL_Apertium_RDF_pipeline.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2020-11-01</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-nexuslinguarum</subfield>
    <subfield code="p">user-pret-a-llod</subfield>
    <subfield code="o">oai:zenodo.org:4322607</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Zaragoza</subfield>
    <subfield code="0">(orcid)0000-0001-6452-7627</subfield>
    <subfield code="a">Jorge Gracia</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Leveraging Linguistic Linked Data for Cross-Lingual Model Transfer in the Pharmaceutical Domain</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-nexuslinguarum</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-pret-a-llod</subfield>
  </datafield>
  <datafield tag="536" ind1=" " ind2=" ">
    <subfield code="c">825182</subfield>
    <subfield code="a">Ready-to-use Multilingual Linked Language Data for Knowledge Services across Sectors</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&lt;p&gt;We describe the use of linguistic linked data to support a cross-lingual transfer framework for sentiment analysis in the pharmaceutical domain. The proposed system dynamically gathers translations from the Linked Open Data (LOD) cloud, particularly from Apertium RDF, in order to project a deep learning-based sentiment classifier from one language to another, thus enabling scalability and avoiding the need of model re-training when transferred across languages. We describe the whole pipeline traversed by the multilingual data, from their conversion into RDF based on a new dynamic and flexible transformation framework, through their linking and publication as linked data, and finally their exploitation in the particular use case. Based on experiments on projecting a sentiment classifier from English to Spanish, we demonstrate how linked data techniques are able to enhance the multilingual capabilities of a deep learning-based approach in a dynamic and scalable way, in a real application scenario from the pharmaceutical domain.&lt;/p&gt;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="g">499-514</subfield>
    <subfield code="b">Springer</subfield>
    <subfield code="z">978-3-030-62465-1</subfield>
    <subfield code="t">The Semantic Web – ISWC 2020 19th International Semantic Web Conference, Part II</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1007/978-3-030-62466-8_31</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
25
37
views
downloads
Views 25
Downloads 37
Data volume 26.7 MB
Unique views 24
Unique downloads 36

Share

Cite as