2020
ACL
ACL 2020
Efficient and High-Quality Neural Machine Translation with OpenNMT
Abstract
AbstractThis paper describes the OpenNMT submissions to the WNGT 2020 efficiency shared task. We explore training and acceleration of Transformer models with various sizes that are trained in a teacher-student setup. We also present a custom and optimized C++ inference engine that enables fast CPU and GPU decoding with few dependencies. By combining additional optimizations and parallelization techniques, we create small, efficient, and high-quality neural machine translation models.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Natural Language Processing
🐣
Hot Topic Early Bird
- model acceleration
Topics
Machine Learning > Application Areas > Efficient Computing
Machine Learning > Application Areas > Knowledge Distillation
Natural Language Processing > Applications > Machine Translation
Deep Learning > Optimization & Theory > Model Compression
Deep Learning > Learning Types > Knowledge Distillation
Deep Learning > Optimization & Theory > Efficient Computing