Exploring Consensus in Machine Translation for Quality Estimation
Carolina Scarton, Lucia Specia · 2014
This paper presents the use of consensus among Machine Translation (MT) systems for the WMT14 Quality Estimation shared task.Consensus is explored here by comparing the MT system output against several alternative machine translations using standard evaluation metrics.Figures extracted from such metrics are used as features to complement baseline prediction models.The hypothesis is that knowing whether the translation of interest is similar or dissimilar to translations from multiple different MT systems can provide useful information regarding the quality of such a translation.