← Back to papers
2018 ACL ACL 2018

Marian: Fast Neural Machine Translation in C++

Abstract

AbstractWe present Marian, an efficient and self-contained Neural Machine Translation framework with an integrated automatic differentiation engine based on dynamic computation graphs. Marian is written entirely in C++. We describe the design of the encoder-decoder framework and demonstrate that a research-friendly toolkit can achieve high training and translation speed.

🌉 Interdisciplinary Bridge — Machine Learning and Natural Language Processing
🧭 Keyword Pioneer — encoder-decoder framework
🐣 Hot Topic Early Bird — neural machine translation
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Deep Learning, Machine Learning, Natural Language Processing, Reinforcement Learning, Speech & Audio

Authors

Marcin Junczys-Dowmunt , Roman Grundkiewicz , Tomasz Dwojak , Hieu Hoang , Kenneth Heafield , Tom Neckermann , Frank Seide , Ulrich Germann , Alham Fikri Aji , Nikolay Bogoychev , André F. T. Martins , Alexandra Birch

Topics

Machine Learning > Optimization & Theory > Optimization Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Machine Translation Natural Language Processing > Generation > Machine Translation Machine Learning > Learning Types > Deep Learning Deep Learning > Learning Types > Deep Learning

Keywords

neural machine translation efficient inference deep learning automatic differentiation encoder-decoder framework dynamic computation graph
Download PDF

Related papers

Economic Event Detection in Company-Specific News Text 2018
Investigating Effective Parameters for Fine-tuning of Word Embeddings Using Only a Small Corpus 2018
SemAxis: A Lightweight Framework to Characterize Domain-Specific Word Semantics Beyond Sentiment 2018
Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer 2018
Affordances in Grounded Language Learning 2018