CLApr 1, 2018
Marian: Fast Neural Machine Translation in C++
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
arXiv:1804.00344v31215 citations
Originality Synthesis-oriented
AI Analysis
This provides a faster toolkit for researchers and practitioners in machine translation, but it is incremental as it builds on existing encoder-decoder methods.
The authors tackled the problem of slow neural machine translation by developing Marian, a C++ framework with integrated automatic differentiation, achieving high training and translation speed.
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.