November 2, 2019 Conference paper Open Access

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

MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="041" ind1=" " ind2=" ">
    <subfield code="a">eng</subfield>
  </datafield>
  <controlfield tag="005">20200120165005.0</controlfield>
  <controlfield tag="001">3525490</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Institute of Anthropomatics and Robotics, KIT, Germany</subfield>
    <subfield code="a">Ha, Thanh-Le</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">University of Engineering and Technology, VNU, Vietnam</subfield>
    <subfield code="a">Nguyen, Phuong-Thai</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">School of Information Science, JAIST, Japan</subfield>
    <subfield code="a">Nguyen, Le-Minh</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">266465</subfield>
    <subfield code="z">md5:5eecea8a3ca3a1487830b867ce8f9a4d</subfield>
    <subfield code="u">https://zenodo.org/record/3525490/files/IWSLT2019_paper_28.pdf</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2019-11-02</subfield>
  </datafield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="p">openaire</subfield>
    <subfield code="p">user-iwslt2019</subfield>
    <subfield code="o">oai:zenodo.org:3525490</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">University of Information and Communication Technology, TNU, Vietnam</subfield>
    <subfield code="a">Ngo, Thi-Vinh</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">How Transformer Revitalizes Character-based Neural Machine Translation: An Investigation on Japanese-Vietnamese Translation Systems</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-iwslt2019</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">https://creativecommons.org/licenses/by/4.0/legalcode</subfield>
    <subfield code="a">Creative Commons Attribution 4.0 International</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="a">cc-by</subfield>
    <subfield code="2">opendefinition.org</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">&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;</subfield>
  </datafield>
  <datafield tag="773" ind1=" " ind2=" ">
    <subfield code="n">doi</subfield>
    <subfield code="i">isVersionOf</subfield>
    <subfield code="a">10.5281/zenodo.3525489</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3525490</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>