November 1, 2020 Conference paper Open Access

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

DataCite XML Export

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="URL">https://zenodo.org/record/4322607</identifier>
  <creators>
    <creator>
      <creatorName>Jorge Gracia</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0001-6452-7627</nameIdentifier>
      <affiliation>University of Zaragoza</affiliation>
    </creator>
    <creator>
      <creatorName>Christian Fäth</creatorName>
      <affiliation>Goethe University Frankfurt</affiliation>
    </creator>
    <creator>
      <creatorName>Matthias Hartung</creatorName>
      <affiliation>Semalytix GmbH</affiliation>
    </creator>
    <creator>
      <creatorName>Max Ionov</creatorName>
      <affiliation>Goethe University Frankfurt</affiliation>
    </creator>
    <creator>
      <creatorName>Julia Bosque-Gil</creatorName>
      <affiliation>University of Zaragoza</affiliation>
    </creator>
    <creator>
      <creatorName>Susana Veríssimo</creatorName>
      <affiliation>Semalytix GmbH</affiliation>
    </creator>
    <creator>
      <creatorName>Christian Chiarcos</creatorName>
      <affiliation>Goethe University Frankfurt</affiliation>
    </creator>
    <creator>
      <creatorName>Matthias Orlikowski</creatorName>
      <affiliation>Semalytix GmbH</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Leveraging Linguistic Linked Data for Cross-Lingual Model Transfer in the Pharmaceutical Domain</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2020</publicationYear>
  <subjects>
    <subject>Apertium RDF, cross-lingual model transfer, Fintan</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2020-11-01</date>
  </dates>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/4322607</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1007/978-3-030-62466-8_31</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/nexuslinguarum</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/pret-a-llod</relatedIdentifier>
  </relatedIdentifiers>
  <version>pre-published version</version>
  <rightsList>
    <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&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;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/501100000780</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/825182/">825182</awardNumber>
      <awardTitle>Ready-to-use Multilingual Linked Language Data for Knowledge Services across Sectors</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>