Unbabel's Participation in the WMT19 Translation Quality Estimation Shared Task
This work addresses translation quality estimation for machine translation systems, but it is incremental as it builds upon existing frameworks and methods.
The Unbabel team tackled the WMT 2019 Shared Task on Quality Estimation across word, sentence, and document levels for three language pairs, achieving the best results by a considerable margin.
We present the contribution of the Unbabel team to the WMT 2019 Shared Task on Quality Estimation. We participated on the word, sentence, and document-level tracks, encompassing 3 language pairs: English-German, English-Russian, and English-French. Our submissions build upon the recent OpenKiwi framework: we combine linear, neural, and predictor-estimator systems with new transfer learning approaches using BERT and XLM pre-trained models. We compare systems individually and propose new ensemble techniques for word and sentence-level predictions. We also propose a simple technique for converting word labels into document-level predictions. Overall, our submitted systems achieve the best results on all tracks and language pairs by a considerable margin.