2019
EMNLP
EMNLP 2019
NICT’s participation to WAT 2019: Multilingualism and Multi-step Fine-Tuning for Low Resource NMT
Abstract
AbstractIn this paper we describe our submissions to WAT 2019 for the following tasks: English–Tamil translation and Russian–Japanese translation. Our team,“NICT-5”, focused on multilingual domain adaptation and back-translation for Russian–Japanese translation and on simple fine-tuning for English–Tamil translation . We noted that multi-stage fine tuning is essential in leveraging the power of multilingualism for an extremely low-resource language like Russian–Japanese. Furthermore, we can improve the performance of such a low-resource language pair by exploiting a small but in-domain monolingual corpus via back-translation. We managed to obtain second rank in both tasks for all translation directions.
🌉
Interdisciplinary Bridge
— Artificial Intelligence and Deep Learning and Machine Learning and Natural Language Processing
🧭
Keyword Pioneer
— multi-step fine-tuning
🐣
Hot Topic Early Bird
— multilingual model
🐝
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
Topics
Artificial Intelligence > Learning Paradigms > Transfer Learning
Machine Learning > Application Areas > Domain Adaptation
Natural Language Processing > Applications > Machine Translation
Machine Learning > Learning Paradigms > Transfer Learning
Machine Learning > Learning Types > Transfer Learning
Natural Language Processing > Generation > Machine Translation
Deep Learning > Learning Types > Fine-Tuning