Conference paper Open Access

NUIG-Panlingua-KMI Hindi↔Marathi MT Systems for SimilarLanguage Translation Task @ WMT 2020

Atul Kr. Ojha; Priya Rani; Akanksha Bansal; Bharathi Raja Chakravarthi; Ritesh Kumar; John P. McCrae


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="DOI">10.5281/zenodo.4320715</identifier>
  <creators>
    <creator>
      <creatorName>Atul Kr. Ojha</creatorName>
      <affiliation>National University of Ireland Galway</affiliation>
    </creator>
    <creator>
      <creatorName>Priya Rani</creatorName>
      <affiliation>National University of Ireland Galway</affiliation>
    </creator>
    <creator>
      <creatorName>Akanksha Bansal</creatorName>
      <affiliation>Panlingua Language Processing LLP</affiliation>
    </creator>
    <creator>
      <creatorName>Bharathi Raja Chakravarthi</creatorName>
      <affiliation>National University of Ireland Galway</affiliation>
    </creator>
    <creator>
      <creatorName>Ritesh Kumar</creatorName>
      <affiliation>Dr. Bhimrao Ambedkar University</affiliation>
    </creator>
    <creator>
      <creatorName>John P. McCrae</creatorName>
      <nameIdentifier nameIdentifierScheme="ORCID" schemeURI="http://orcid.org/">0000-0002-7227-1331</nameIdentifier>
      <affiliation>National University of Ireland Galway</affiliation>
    </creator>
  </creators>
  <titles>
    <title>NUIG-Panlingua-KMI Hindi↔Marathi MT Systems for SimilarLanguage Translation Task @ WMT 2020</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2020</publicationYear>
  <dates>
    <date dateType="Issued">2020-11-19</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/4320715</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.4320714</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/elexis</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;NUIG-Panlingua-KMI submission to WMT 2020 seeks to push the state-of-the-art in Similar Language Translation Task for Hindi &amp;lt;-&amp;gt; Marathi language pair. As part of these efforts, we conducted a series of experiments to address the challenges for translation between similar languages. Among the 4 MT systems prepared under this task, 1 PBSMT systems were prepared for Hindi &amp;lt;-&amp;gt; Marathi each and 1 NMT systems were developed for Hindi &amp;lt;-&amp;gt; Marathi using Byte Pair En-coding (BPE) into subwords. The results show that different architectures in NMT could be an effective method for developing MT systems for closely related languages. Our Hindi-Marathi NMT system was ranked 8th among the 14 teams that participated and our Marathi-Hindi NMT system was ranked 8th among the 11 teams participated for the task.&lt;/p&gt;</description>
  </descriptions>
  <fundingReferences>
    <fundingReference>
      <funderName>European Commission</funderName>
      <funderIdentifier funderIdentifierType="Crossref Funder ID">10.13039/100010661</funderIdentifier>
      <awardNumber awardURI="info:eu-repo/grantAgreement/EC/H2020/731015/">731015</awardNumber>
      <awardTitle>European Lexicographic Infrastructure</awardTitle>
    </fundingReference>
  </fundingReferences>
</resource>
23
12
views
downloads
All versions This version
Views 2323
Downloads 1212
Data volume 5.0 MB5.0 MB
Unique views 1717
Unique downloads 1212

Share

Cite as