Conference paper Open Access

Integrating Domain Terminology into Neural Machine Translation

Elise Michon; Josep Crego; Jean Senellart


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/4537095</identifier>
  <creators>
    <creator>
      <creatorName>Elise Michon</creatorName>
      <affiliation>SYSTRAN</affiliation>
    </creator>
    <creator>
      <creatorName>Josep Crego</creatorName>
      <affiliation>SYSTRAN</affiliation>
    </creator>
    <creator>
      <creatorName>Jean Senellart</creatorName>
      <affiliation>SYSTRAN</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Integrating Domain Terminology into Neural Machine Translation</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2020</publicationYear>
  <subjects>
    <subject>Neural Machine Translation</subject>
    <subject>Terminology</subject>
    <subject>Domain Adaptation</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2020-12-08</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/4537095</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsDerivedFrom" resourceTypeGeneral="ConferencePaper">10.18653/v1/2020.coling-main.348</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.18653/v1/2020.coling-main.348</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/787061</relatedIdentifier>
  </relatedIdentifiers>
  <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;This paper extends existing work on terminology integration into Neural Machine Translation, a common industrial practice to dynamically adapt translation to a specific domain. Our method, based on the use of placeholders complemented with morphosyntactic annotation, efficiently taps into the ability of the neural network to deal with symbolic knowledge to surpass the surface generalization shown by alternative techniques. We compare our approach to state-of-the-art systems and benchmark them through a well-defined evaluation framework, focusing on actual application of terminology and not just on the overall performance. Results indicate the suitability of our method in the use-case where terminology is used in a system trained on generic data only.&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/H2020/787061/">787061</awardNumber>
      <awardTitle>Advanced tools for fighting oNline Illegal TrAfficking</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
38
27
views
downloads
Views 38
Downloads 27
Data volume 7.2 MB
Unique views 27
Unique downloads 26

Share

Cite as