Quality Estimation-Assisted Automatic Post-Editing
Sourabh Deoghare, Diptesh Kanojia, Frédéric Blain, Tharindu Ranasinghe, Pushpak Bhattacharyya · 2023
Automatic Post-Editing (APE) systems are prone to over-correction of the Machine Translation (MT) outputs.While a Word-level Quality Estimation (QE) system can provide a way to curtail the over-correction, a significant performance gain has not been observed thus far by utilizing existing APE and QE combination strategies.This paper proposes joint training of a model over QE (sentence-and word-level) and APE tasks to improve the APE.Our proposed approach utilizes a multi-task learning (MTL) methodology, which shows significant improvement while treating the tasks as a 'bargaining game' during training.Moreover, we investigate various existing combination strategies and show that our approach achieves stateof-the-art performance for a 'distant' language pair, viz., English-Marathi.We observe an improvement of 1.09 TER and 1.37 BLEU points over a baseline QE-Unassisted APE system for English-Marathi while also observing 0.46 TER and 0.62 BLEU points improvement for English-German.Further, we discuss the results qualitatively and show how our approach helps reduce over-correction, thereby improving the APE performance.We also observe that the degree of integration between QE and APE directly correlates with the APE performance gain.We release our code publicly 1 .