Conference paper Open Access

KIT's Submission to the IWSLT 2019 Shared Task on Text Translation

Schneider, Felix; Waibel, Alex


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.3525496</identifier>
  <creators>
    <creator>
      <creatorName>Schneider, Felix</creatorName>
      <givenName>Felix</givenName>
      <familyName>Schneider</familyName>
      <affiliation>Karlsruhe Institute of Technology</affiliation>
    </creator>
    <creator>
      <creatorName>Waibel, Alex</creatorName>
      <givenName>Alex</givenName>
      <familyName>Waibel</familyName>
      <affiliation>Karlsruhe Institute of Technology</affiliation>
    </creator>
  </creators>
  <titles>
    <title>KIT's Submission to the IWSLT 2019 Shared Task on Text Translation</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <dates>
    <date dateType="Issued">2019-11-02</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3525496</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3525495</relatedIdentifier>
    <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/iwslt2019</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;In this paper, we describe KIT&amp;rsquo;s submission for the IWSLT 2019 shared task on text translation. Our system is based on the transformer model [1] using our in-house implementation. We augment the available training data using back-translation and employ fine-tuning for the final model. For our best results, we used a 12-layer&amp;nbsp;transformer-big&amp;nbsp;config- uration, achieving state-of-the-art results on the WMT2018 test set. We also experiment with student-teacher models to improve performance of smaller models.&lt;/p&gt;</description>
  </descriptions>
</resource>
116
86
views
downloads
All versions This version
Views 116115
Downloads 8686
Data volume 8.2 MB8.2 MB
Unique views 102101
Unique downloads 8080

Share

Cite as