SHEF-Lite 2.0: Sparse Multi-task Gaussian Processes for Translation Quality Estimation
Daniel Beck, Kashif Ur Rehman Shah, Lucia Specia · 2014
We describe our systems for the WMT14 Shared Task on Quality Estimation (subtasks 1.1, 1.2 and 1.3).Our submissions use the framework of Multi-task Gaussian Processes, where we combine multiple datasets in a multi-task setting.Due to the large size of our datasets we also experiment with Sparse Gaussian Processes, which aim to speed up training and prediction by providing sensible sparse approximations.