Conference paper Open Access

How Transformer Revitalizes Character-based Neural Machine Translation: An Investigation on Japanese-Vietnamese Translation Systems

Ngo, Thi-Vinh; Ha, Thanh-Le; Nguyen, Phuong-Thai; Nguyen, Le-Minh


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.3525490</identifier>
  <creators>
    <creator>
      <creatorName>Ngo, Thi-Vinh</creatorName>
      <givenName>Thi-Vinh</givenName>
      <familyName>Ngo</familyName>
      <affiliation>University of Information and Communication Technology, TNU, Vietnam</affiliation>
    </creator>
    <creator>
      <creatorName>Ha, Thanh-Le</creatorName>
      <givenName>Thanh-Le</givenName>
      <familyName>Ha</familyName>
      <affiliation>Institute of Anthropomatics and Robotics, KIT, Germany</affiliation>
    </creator>
    <creator>
      <creatorName>Nguyen, Phuong-Thai</creatorName>
      <givenName>Phuong-Thai</givenName>
      <familyName>Nguyen</familyName>
      <affiliation>University of Engineering and Technology, VNU, Vietnam</affiliation>
    </creator>
    <creator>
      <creatorName>Nguyen, Le-Minh</creatorName>
      <givenName>Le-Minh</givenName>
      <familyName>Nguyen</familyName>
      <affiliation>School of Information Science, JAIST, Japan</affiliation>
    </creator>
  </creators>
  <titles>
    <title>How Transformer Revitalizes Character-based Neural Machine Translation: An Investigation on Japanese-Vietnamese Translation Systems</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/3525490</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3525489</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;While translating between East Asian languages, many works have discovered clear advantages of using characters as the translation unit. Unfortunately, traditional recurrent neural machine translation systems hinder the practical usage of those character-based systems due to their architectural limitations. They are unfavorable in handling extremely long sequences as well as highly restricted in parallelizing the computations. In this paper, we demonstrate that the new transformer architecture can perform character-based trans- lation better than the recurrent one. We conduct experiments on a low-resource language pair: Japanese-Vietnamese. Our models considerably outperform the state-of-the-art systems which employ word-based recurrent architectures.&lt;/p&gt;</description>
  </descriptions>
</resource>
90
74
views
downloads
All versions This version
Views 9091
Downloads 7475
Data volume 19.7 MB20.0 MB
Unique views 8283
Unique downloads 7374

Share

Cite as