Conference paper Open Access

Controlling Utterance Length in NMT-based Word Segmentation with Attention

Godard, Pierre; Besacier, Laurent; Yvon, François


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:cnt="http://www.w3.org/2011/content#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.3524959">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Text"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.3524959</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3524959"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Godard, Pierre</foaf:name>
        <foaf:givenName>Pierre</foaf:givenName>
        <foaf:familyName>Godard</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>LIMSI, CNRS, Université Paris-Saclay, F 91 405 Orsay &amp; LIG, CNRS et Université Grenoble Alpes, F 38 000 Grenoble</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Besacier, Laurent</foaf:name>
        <foaf:givenName>Laurent</foaf:givenName>
        <foaf:familyName>Besacier</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>LIG, CNRS et Université Grenoble Alpes, F 38 000 Grenoble</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Yvon, François</foaf:name>
        <foaf:givenName>François</foaf:givenName>
        <foaf:familyName>Yvon</foaf:familyName>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>LIMSI, CNRS, Université Paris-Saclay, F 91 405 Orsay</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>Controlling Utterance Length in NMT-based Word Segmentation with Attention</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2019</dct:issued>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2019-11-02</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3524959"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3524959</skos:notation>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3524958"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/iwslt2019"/>
    <dct:description>&lt;p&gt;One of the basic tasks of computational language documentation (CLD) is to identify word boundaries in an unsegmented phonemic stream. While several unsupervised monolingual word segmentation algorithms exist in the literature, they are challenged in real-world CLD settings by the small amount of available data. A possible remedy is to take advantage of glosses or translation in a foreign, well- resourced, language, which often exist for such data. In this paper, we explore and compare ways to exploit neural machine translation models to perform unsupervised boundary detection with bilingual information, notably introducing a new loss function for jointly learning alignment and segmentation. We experiment with an actual under-resourced language, Mboshi, and show that these techniques can effectively control the output segmentation length.&lt;/p&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dct:rights>
          <dct:RightsStatement rdf:about="https://creativecommons.org/licenses/by/4.0/legalcode">
            <rdfs:label>Creative Commons Attribution 4.0 International</rdfs:label>
          </dct:RightsStatement>
        </dct:rights>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3524959"/>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
72
42
views
downloads
All versions This version
Views 7267
Downloads 4242
Data volume 23.4 MB23.4 MB
Unique views 6762
Unique downloads 4040

Share

Cite as