Skip to content
conftrace_
2021 EMNLP EMNLP 2021

IST-Unbabel 2021 Submission for the Quality Estimation Shared Task

Abstract

AbstractWe 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.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Chrysoula Zerva, Daan van Stigt, Ricardo Rei, Ana C Farinha, Pedro Ramos, José G. C. de Souza, Taisiya Glushkova, Miguel Vera, Fabio Kepler, André F. T. Martins

Topics

Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Machine Translation Machine Learning > Learning Types > Multi-Task Learning Deep Learning > Learning Types > Transfer Learning Machine Learning > Learning Types > Multi-Lingual Learning

Keywords

uncertainty modeling machine translation quality estimation multilingual model multilingual encoder post-editing effort direct assessment uncertainty objective
Download PDF

More from EMNLP 2021

All EMNLP 2021 papers →
NICT Kyoto Submission for the WMT’21 Quality Estimation Task: Multimetric Multilingual Pretraining for Critical Error Detection
QEMind: Alibaba’s Submission to the WMT21 Quality Estimation Shared Task
Direct Exploitation of Attention Weights for Translation Quality Estimation
The IICT-Yverdon System for the WMT 2021 Unsupervised MT and Very Low Resource Supervised MT Task
Unsupervised Translation of German–Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language
The LMU Munich Systems for the WMT21 Unsupervised and Very Low-Resource Translation Task