Estimating post-editing effort: a study on human judgements, task-based and reference-based metrics of MT quality
This work addresses the challenge of evaluating machine translation quality for post-editing tasks, which is important for MT practitioners, but it is incremental as it builds on existing metric comparisons without introducing new methods.
The paper tackled the problem of estimating post-editing effort in machine translation by comparing human judgements, task-based metrics, and reference-based metrics, finding that task-based metrics (e.g., comparing machine-translated and post-edited versions) are the best at tracking effort, followed by direct assessments and then reference-based metrics.
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 judgements, 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 detailed 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 deciding how to evaluate MT for post-editing purposes.