Skip to content
conftrace_
2022 EMNLP EMNLP 2022

MUNI-NLP Systems for Lower Sorbian-German and Lower Sorbian-Upper Sorbian Machine Translation @ WMT22

Abstract

AbstractWe describe our neural machine translation systems for the WMT22 shared task on unsupervised MT and very low resource supervised MT. We submit supervised NMT systems for Lower Sorbian-German and Lower Sorbian-Upper Sorbian translation in both directions. By using a novel tokenization algorithm, data augmentation techniques, such as Data Diversification (DD), and parameter optimization we improve on our baselines by 10.5-10.77 BLEU for Lower Sorbian-German and by 1.52-1.88 BLEU for Lower Sorbian-Upper Sorbian.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Edoardo Signoroni, Pavel Rychlý

Topics

Machine Learning > Application Areas > Data Augmentation Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Machine Translation Machine Learning > Learning Types > Transfer Learning Deep Learning > Learning Types > Transfer Learning

Keywords

data augmentation neural machine translation parameter optimization low-resource translation tokenization algorithm data diversification
Download PDF

More from EMNLP 2022

All EMNLP 2022 papers →
ANVITA-African: A Multilingual Neural Machine Translation System for African Languages
HW-TSC Systems for WMT22 Very Low Resource Supervised MT Task
Unsupervised and Very-Low Resource Supervised Translation on German and Sorbian Variant Languages
The AIC System for the WMT 2022 Unsupervised MT and Very Low Resource Supervised MT Task
NICT at MixMT 2022: Synthetic Code-Mixed Pre-training and Multi-way Fine-tuning for Hinglish–English Translation
Gui at MixMT 2022 : English-Hinglish : An MT Approach for Translation of Code Mixed Data