November 2, 2019 Conference paper Open Access

Macé, Valentin; Servan, Christophe

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">20200120161145.0</controlfield>
  <controlfield tag="001">3525020</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">QWANT RESEARCH - 7 Rue Spontini, 75116 Paris, France</subfield>
    <subfield code="a">Servan, Christophe</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">168252</subfield>
    <subfield code="z">md5:3a4a4614e5f77e181163dafd99370339</subfield>
    <subfield code="u">https://zenodo.org/record/3525020/files/IWSLT2019_paper_20.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:3525020</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">QWANT RESEARCH - 7 Rue Spontini, 75116 Paris, France</subfield>
    <subfield code="a">Macé, Valentin</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Using Whole Document Context in Neural Machine Translation</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;In Machine Translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a simple yet promising approach to add contextual information in Neural Machine Translation. We present a method to add source context that capture the whole document with accurate boundaries, taking every word into account. We provide this additional information to a Transformer model and study the impact of our method on three language pairs. The proposed approach obtains promising results in the English-German, English-French and French-English document-level translation tasks. We observe interesting cross-sentential behaviors where the model learns to use document-level information to improve translation coherence.&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.3525019</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3525020</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>