← Back to papers
2022 EMNLP EMNLP 2022

Samsung R&D Institute Poland Participation in WMT 2022

Abstract

AbstractThis paper presents the system description of Samsung R&D Institute Poland participation in WMT 2022 for General MT solution for medium and low resource languages: Russian and Croatian. Our approach combines iterative noised/tagged back-translation and iterative distillation. We investigated different monolingual resources and compared their influence on final translations. We used available BERT-likemodels for text classification and for extracting domains of texts. Then we prepared an ensemble of NMT models adapted to multiple domains. Finally we attempted to predict ensemble weight vectors from the BERT-based domain classifications for individual sentences. Our final trained models reached quality comparable to best online translators using only limited constrained resources during training.

🌉 Interdisciplinary Bridge — Deep Learning and Machine Learning and Natural Language Processing
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio

Authors

Adam Dobrowolski , Mateusz Klimaszewski , Adam Myśliwy , Marcin Szymański , Jakub Kowalski , Kornelia Szypuła , Paweł Przewłocki , Paweł Przybysz

Topics

Machine Learning > Application Areas > Knowledge Distillation Natural Language Processing > Applications > Machine Translation Deep Learning > Learning Types > Knowledge Distillation Deep Learning > Learning Types > Transfer Learning

Keywords

domain adaptation ensemble learning knowledge distillation neural machine translation domain classification
Download PDF

Related papers

Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport 2022
Generative Entity Typing with Curriculum Learning 2022
Towards Reinterpreting Neural Topic Models via Composite Activations 2022
Weakly Supervised Headline Dependency Parsing 2022
Cross-modal Transfer Between Vision and Language for Protest Detection 2022