Skip to content
conftrace_
2021 EMNLP EMNLP 2021

RTM Super Learner Results at Quality Estimation Task

Abstract

AbstractWe obtain new results using referential translation machines (RTMs) with predictions mixed to obtain a better mixture of experts prediction. Our super learner results improve the results and provide a robust combination model.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Ergun Biçici

Topics

Natural Language Processing > Applications > Machine Translation Machine Learning > Learning Types > Ensemble Learning Machine Learning > Core Methods > Ensemble Methods Natural Language Processing > Applications > Quality Estimation

Keywords

ensemble learning model combination quality estimation mixture of expert prediction mixing referential translation machine super learner
Download PDF

More from EMNLP 2021

All EMNLP 2021 papers →
Huawei AARC’s Submissions to the WMT21 Biomedical Translation Task: Domain Adaption from a Practical Perspective
Tencent AI Lab Machine Translation Systems for the WMT21 Biomedical Translation Task
HW-TSC’s Submissions to the WMT21 Biomedical Translation Task
HW-TSC’s Participation at WMT 2021 Quality Estimation Shared Task
Ensemble Fine-tuned mBERT for Translation Quality Estimation
The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task