November 2, 2019 Conference paper Open Access

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

JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>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&nbsp;direct assessments&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&nbsp;judgements&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&nbsp;measurements&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.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Department of Computer Science, University of Sheffield, Sheffield S1 4DP, UK", 
      "@type": "Person", 
      "name": "Scarton, Scarton"
    }, 
    {
      "affiliation": "Dept. Llenguatges i Sist. Inform., Universitat d'Alacant, 03690 St. Vicent del Raspeig, Spain", 
      "@type": "Person", 
      "name": "Forcada, Mikel L."
    }, 
    {
      "affiliation": "Dept. Llenguatges i Sist. Inform., Universitat d'Alacant, 03690 St. Vicent del Raspeig, Spain", 
      "@type": "Person", 
      "name": "Espl\u00e0-Gomis, Miquel"
    }, 
    {
      "affiliation": "Department of Computer Science, University of Sheffield, Sheffield S1 4DP, UK & Department of Computing, Imperial College London, London SW7 2AZ, UK", 
      "@type": "Person", 
      "name": "Specia, Lucia"
    }
  ], 
  "headline": "Estimating post-editing effort: a study on human judgements, task-based and reference-based metrics of MT quality", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2019-11-02", 
  "url": "https://zenodo.org/record/3525003", 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.3525003", 
  "@id": "https://doi.org/10.5281/zenodo.3525003", 
  "@type": "ScholarlyArticle", 
  "name": "Estimating post-editing effort: a study on human judgements, task-based and reference-based metrics of MT quality"
}