Creating and sharing knowledge for telecommunications

IST-Unbabel 2021 Submission for the Quality Estimation Shared Task

Zerva, C ; Stigt, D. ; Rei , R. ; Farinha, A. C. ; Ramos, P. G. ; de Souza, J. G. ; Glushkova, T. ; Vera, M. ; Kepler, F. ; Martins, A.

IST-Unbabel 2021 Submission for the Quality Estimation Shared Task, Proc Conference on Machine Translation WMT, Conference Online, Vol. , pp. - , November, 2021.

Digital Object Identifier:

Download Full text PDF ( 339 KBs)

Abstract
We present the joint contribution of IST and Unbabel to the WMT 2021 Shared Task on Quality Estimation. Our team participated on two tasks: Direct Assessment and Post-Editing Effort, encompassing a total of 35 submissions. For all submissions, our efforts focused on training multilingual models on top of OpenKiwi predictor-estimator architecture, using pre-trained multilingual encoders combined with adapters. We further experiment with and uncertainty-related objectives and features as well as training on out-of-domain direct assessment data.