November 2, 2019 Conference paper Open Access

Scarton, Scarton; Forcada, Mikel L.; Esplà-Gomis, Miquel; Specia, Lucia

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">20200120173440.0</controlfield>
  <controlfield tag="001">3525003</controlfield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Dept. Llenguatges i Sist. Inform., Universitat d'Alacant, 03690 St. Vicent del Raspeig, Spain</subfield>
    <subfield code="a">Forcada, Mikel L.</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Dept. Llenguatges i Sist. Inform., Universitat d'Alacant, 03690 St. Vicent del Raspeig, Spain</subfield>
    <subfield code="a">Esplà-Gomis, Miquel</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Department of Computer Science, University of Sheffield, Sheffield S1 4DP, UK &amp; Department of Computing, Imperial College London, London SW7 2AZ, UK</subfield>
    <subfield code="a">Specia, Lucia</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="s">428595</subfield>
    <subfield code="z">md5:92181f24bdccacf2a7f0f42c7b27fee9</subfield>
    <subfield code="u">https://zenodo.org/record/3525003/files/IWSLT2019_paper_18.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:3525003</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Department of Computer Science, University of Sheffield, Sheffield S1 4DP, UK</subfield>
    <subfield code="a">Scarton, Scarton</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Estimating post-editing effort: a study on human judgements, task-based and reference-based metrics of MT quality</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;Devising metrics to assess translation quality has always been at the core of machine translation (MT) research. Traditional automatic reference-based metrics, such as BLEU, have shown correlations with human judgements of adequacy and fluency and have been paramount for the advancement of MT system development. Crowd-sourcing has popularised and enabled the scalability of metrics based on human judgments, such as subjective&amp;nbsp;direct assessments&amp;nbsp;(DA) of adequacy, that are believed to be more reliable than reference-based automatic metrics. Finally, task-based measurements, such as post-editing time, are expected to provide a more de- tailed evaluation of the usefulness of translations for a specific task. Therefore, while DA averages adequacy&amp;nbsp;judgements&amp;nbsp;to obtain an appraisal of (perceived) quality independently of the task, and reference-based automatic metrics try to objectively estimate quality also in a task-independent way, task-based metrics are&amp;nbsp;measurements&amp;nbsp;obtained either during or after performing a specific task. In this paper we argue that, although expensive, task-based measurements are the most reliable when estimating MT quality in a specific task; in our case, this task is post-editing. To that end, we report experiments on a dataset with newly-collected post-editing indicators and show their usefulness when estimating post-editing effort. Our results show that task-based metrics comparing machine-translated and post-edited versions are the best at tracking post-editing effort, as expected. These metrics are followed by DA, and then by metrics comparing the machine-translated version and independent references. We suggest that MT practitioners should be aware of these differences and acknowledge their implications when decid- ing how to evaluate MT for post-editing purposes.&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.3525002</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.5281/zenodo.3525003</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">conferencepaper</subfield>
  </datafield>
</record>