Ensembling Factored Neural Machine Translation Models for Automatic Post-Editing and Quality Estimation
This work addresses quality improvement and estimation in machine translation for users relying on automated systems, but it is incremental as it combines existing approaches within a single framework.
The paper tackled the problems of Automatic Post-Editing (APE) and Word-Level Quality Estimation (QE) by ensembling specialized Neural Machine Translation models with input factors, achieving state-of-the-art results in both tasks through a tuning step that learns ensemble weights.
This work presents a novel approach to Automatic Post-Editing (APE) and Word-Level Quality Estimation (QE) using ensembles of specialized Neural Machine Translation (NMT) systems. Word-level features that have proven effective for QE are included as input factors, expanding the representation of the original source and the machine translation hypothesis, which are used to generate an automatically post-edited hypothesis. We train a suite of NMT models that use different input representations, but share the same output space. These models are then ensembled together, and tuned for both the APE and the QE task. We thus attempt to connect the state-of-the-art approaches to APE and QE within a single framework. Our models achieve state-of-the-art results in both tasks, with the only difference in the tuning step which learns weights for each component of the ensemble.