Can I read The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task on EtoBox?

The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task by Ding, Shuoyang; Junczys-Dowmunt, Marcin; Post, Matt; Federmann, Christian; Koehn, Philipp is a scholarly article available to read on EtoBox.

What is The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task about?

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.

Author

Ding, Shuoyang; Junczys-Dowmunt, Marcin; Post, Matt; Federmann, Christian; Koehn, Philipp

Published

2021

Language

EN