Back to Search
Start Over
Marian: Fast Neural Machine Translation in C++
- Publication Year :
- 2018
-
Abstract
- We 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.<br />Comment: Demonstration paper
- Subjects :
- Computer Science - Computation and Language
Subjects
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.1804.00344
- Document Type :
- Working Paper