Info: Zenodo’s user support line is staffed on regular business days between Dec 23 and Jan 5. Response times may be slightly longer than normal.

Published November 2, 2019 | Version v1
Conference paper Open

Estimating post-editing effort: a study on human judgements, task-based and reference-based metrics of MT quality

  • 1. Department of Computer Science, University of Sheffield, Sheffield S1 4DP, UK
  • 2. Dept. Llenguatges i Sist. Inform., Universitat d'Alacant, 03690 St. Vicent del Raspeig, Spain
  • 3. Department of Computer Science, University of Sheffield, Sheffield S1 4DP, UK & Department of Computing, Imperial College London, London SW7 2AZ, UK

Description

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 direct assessments (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 judgements 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 measurements 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.

Files

IWSLT2019_paper_18.pdf

Files (428.6 kB)

Name Size Download all
md5:92181f24bdccacf2a7f0f42c7b27fee9
428.6 kB Preview Download