November 2, 2019 Conference paper Open Access

Nguyen, Ha

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.3525556</identifier>
  <creators>
    <creator>
      <creatorName>Nguyen, Ha</creatorName>
      <givenName>Ha</givenName>
      <familyName>Nguyen</familyName>
      <affiliation>LIG - Universite ́ Grenoble Alpes, France</affiliation>
    </creator>
  </creators>
  <titles>
    <title>ON-TRAC Consortium End-to-End Speech Translation Systems for the IWSLT 2019 Shared Task</title>
  </titles>
  <publisher>Zenodo</publisher>
  <publicationYear>2019</publicationYear>
  <dates>
    <date dateType="Issued">2019-11-02</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="ConferencePaper"/>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3525556</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3525555</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;This paper describes the ON-TRAC Consortium translation systems developed for the end-to-end model task of IWSLT Evaluation 2019 for the English&amp;rarr;&amp;nbsp;Portuguese language pair. ON-TRAC Consortium is composed of researchers from three French academic laboratories: LIA (Avignon Universit&amp;eacute;), LIG (Universit&amp;eacute;&amp;nbsp;Grenoble Alpes), and LIUM (Le Mans Universit&amp;eacute;). A single end-to-end model built as a neural encoder-decoder architecture with attention mechanism was used for two primary submissions corresponding to the two EN-PT evaluations sets: (1) TED (MuST-C) and (2) How2. In this paper, we notably investigate impact of pooling heterogeneous corpora for training, impact of target tokenization (characters or BPEs), impact of speech input segmentation and we also compare our best end-to-end model (BLEU of 26.91 on MuST-C and 43.82 on How2 validation sets) to a pipeline (ASR+MT) approach.&lt;/p&gt;</description>
  </descriptions>
</resource>