Pushing the Limits of Translation Quality Estimation
TACL, Volume 5, 2017, Pages 205-218.
We have presented new state of the art systems for word-level and sentence-level quality estimation that are considerably more accurate than previous systems on the WMT15 and WMT16 datasets
Translation quality estimation is a task of growing importance in NLP, due to its potential to reduce post-editing human effort in disruptive ways. However, this potential is currently limited by the relatively low accuracy of existing systems. In this paper, we achieve remarkable improvements by exploiting synergies between the related t...More
PPT (Upload PPT)