Conference paper Open Access

Neural Baselines for Word Alignment

Ho, Anh Khoa Ngo; Yvon, François


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.3525026</identifier>
  <creators>
    <creator>
      <creatorName>Ho, Anh Khoa Ngo</creatorName>
      <givenName>Anh Khoa Ngo</givenName>
      <familyName>Ho</familyName>
      <affiliation>LIMSI, CNRS, Université Paris-Saclay, Baˆt. 508, rue John von Neumann, Campus Universitaire, F-91405 Orsay</affiliation>
    </creator>
    <creator>
      <creatorName>Yvon, François</creatorName>
      <givenName>François</givenName>
      <familyName>Yvon</familyName>
      <affiliation>LIMSI, CNRS, Université Paris-Saclay, Baˆt. 508, rue John von Neumann, Campus Universitaire, F-91405 Orsay</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Neural Baselines for Word Alignment</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <dates>
    <date dateType="Issued">2019-11-02</date>
  </dates>
  <resourceType resourceTypeGeneral="Text">Conference paper</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3525026</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3525025</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;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;</description>
  </descriptions>
</resource>
112
92
views
downloads
All versions This version
Views 112111
Downloads 9290
Data volume 28.6 MB28.0 MB
Unique views 104103
Unique downloads 8584

Share

Cite as