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.
Citation information
Junczys-Dowmunt, M, Grundkiewicz, R, Dwojak, T, Hoang, H, Heafield, K, Neckermann, T, Seide, F, Germann, U, Aji, AF, Bogoychev, N, Martins, AFT & Birch-Mayne, A 2018, Marian: Fast Neural Machine Translation in C++. in The 56th Annual Meeting of the Association for Computational Linguistics. 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Australia, 15-20 July 2018.
Turing affiliated authors