Conference paper Open Access

Neural Baselines for Word Alignment

Ho, Anh Khoa Ngo; Yvon, François


MARC21 XML Export

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <controlfield tag="005">20200120172858.0</controlfield>
  <controlfield tag="001">3525026</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">LIMSI, CNRS, Université Paris-Saclay, Baˆt. 508, rue John von Neumann, Campus Universitaire, F-91405 Orsay</subfield>
    <subfield code="a">Yvon, François</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">311102</subfield>
    <subfield code="z">md5:8aa1a0901fb5a22f51a9126b88e71ae0</subfield>
    <subfield code="u">https://zenodo.org/record/3525026/files/IWSLT2019_paper_23.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:3525026</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">LIMSI, CNRS, Université Paris-Saclay, Baˆt. 508, rue John von Neumann, Campus Universitaire, F-91405 Orsay</subfield>
    <subfield code="a">Ho, Anh Khoa Ngo</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Neural Baselines for Word Alignment</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;Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems, or to perform quality estimation. In most areas of natural lan- guage processing, neural network models nowadays constitute the preferred approach, a situation that might also apply to word align- ment models. In this work, we study and comprehensively evaluate neural models for unsupervised word alignment for four language pairs, contrasting several variants of neural models. We show that in most settings, neural versions of the IBM-1 and hidden Markov models vastly outperform their discrete counterparts. We also analyze typical alignment errors of the baselines that our models over- come to illustrate the benefits &amp;mdash; and the limitations &amp;mdash; of these new models for morphologically rich languages.&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.3525025</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3525026</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>
109
92
views
downloads
All versions This version
Views 109108
Downloads 9290
Data volume 28.6 MB28.0 MB
Unique views 103102
Unique downloads 8584

Share

Cite as