2018 ACL ACL 2018

Marian: Cost-effective High-Quality Neural Machine Translation in C++

Abstract

AbstractThis paper describes the submissions of the β€œMarian” team to the WNMT 2018 shared task. We investigate combinations of teacher-student training, low-precision matrix products, auto-tuning and other methods to optimize the Transformer model on GPU and CPU. By further integrating these methods with the new averaging attention networks, a recently introduced faster Transformer variant, we create a number of high-quality, high-performance models on the GPU and CPU, dominating the Pareto frontier for this shared task.

πŸŒ‰ Interdisciplinary Bridge β€” Artificial Intelligence and Machine Learning and Natural Language Processing
πŸ“ˆ Trend Setter β€” Model Compression
🧭 Keyword Pioneer β€” transformer model
🐣 Hot Topic Early Bird β€” neural machine translation
🐝 Cross-Pollinator β€” Artificial Intelligence, Computer Vision, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Speech & Audio