The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task
This work addresses quality estimation for machine translation post-editing, but it is incremental as it builds on existing shared task frameworks and methods.
The authors tackled the problem of target-side word-level quality estimation for machine translation post-editing effort, achieving top performance on the MT MCC metric for English-German and demonstrating competitiveness against the OpenKiwi-XLM baseline.
This paper presents the JHU-Microsoft joint submission for WMT 2021 quality estimation shared task. We only participate in Task 2 (post-editing effort estimation) of the shared task, focusing on the target-side word-level quality estimation. The techniques we experimented with include Levenshtein Transformer training and data augmentation with a combination of forward, backward, round-trip translation, and pseudo post-editing of the MT output. We demonstrate the competitiveness of our system compared to the widely adopted OpenKiwi-XLM baseline. Our system is also the top-ranking system on the MT MCC metric for the English-German language pair.