Marian: Cost-effective High-Quality Neural Machine Translation in C++

2018/05/30 by Marcin Junczys-Dowmunt, Junczys-Dowmunt, Marcin, Kenneth Heafield +7 · 2 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1805.12096

openalex publication_date 2018/05/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

This paper describes the submissions of the "Marian" team to the WNMT 2018 shared task. We investigate combinations of teacher-student training, low-precision matrix products, auto-tuning and other methods to optimize the Transformer model on GPU and CPU. By further integrating these methods with the new averaging attention networks, a recently introduced faster Transformer variant, we create a number of high-quality, high-performance models on the GPU and CPU, dominating the Pareto frontier for this shared task.

Cited by

• Findings of the Second Workshop on Neural Machine Translation and Generation
• MoVoC: Morphology-Aware Subword Construction for Geez Script Languages

Related

• Marian: Fast Neural Machine Translation in C++
• Fast Neural Machine Translation Implementation
• CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++
• Exploring Hyper-Parameter Optimization for Neural Machine Translation on GPU Architectures
• Efficient Inference For Neural Machine Translation