The NiuTrans System for the WMT 2021 Efficiency Task
Chenglong Wang, Chi Hu, Yongyu Mu, Zhongxiang Yan, Siming Wu, Yimin Hu, Hang Cao, Bei Li, Ye Lin, Tong Xiao, Jingbo Zhu
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
This paper describes the NiuTrans system for the WMT21 translation efficiency task. Following last year’s work, we explore various techniques to improve the efficiency while maintaining translation quality. We investigate the combinations of lightweight Transformer architectures and knowledge distillation strategies. Also, we improve the translation efficiency with graph optimization, low precision, dynamic batching, and parallel pre/post-processing. Putting these together, our system can translate 247,000 words per second on an NVIDIA A100, being 3 faster than our last year’s system. Our system is the fastest and has the lowest memory consumption on the GPU-throughput track. The code, model, and pipeline will be available at NiuTrans.NMT.