The NiuTrans System for WNGT 2020 Efficiency Task

Chi Hu, Bei Li, Yinqiao Li, Ye Lin, Yanyang Li, Chenglong Wang, Tong Xiao, Jingbo Zhu


Abstract
This paper describes the submissions of the NiuTrans Team to the WNGT 2020 Efficiency Shared Task. We focus on the efficient implementation of deep Transformer models (Wang et al., 2019; Li et al., 2019) using NiuTensor, a flexible toolkit for NLP tasks. We explored the combination of deep encoder and shallow decoder in Transformer models via model compression and knowledge distillation. The neural machine translation decoding also benefits from FP16 inference, attention caching, dynamic batching, and batch pruning. Our systems achieve promising results in both translation quality and efficiency, e.g., our fastest system can translate more than 40,000 tokens per second with an RTX 2080 Ti while maintaining 42.9 BLEU on newstest2018.
Anthology ID:
2020.ngt-1.24
Volume:
Proceedings of the Fourth Workshop on Neural Generation and Translation
Month:
July
Year:
2020
Address:
Online
Editors:
Alexandra Birch, Andrew Finch, Hiroaki Hayashi, Kenneth Heafield, Marcin Junczys-Dowmunt, Ioannis Konstas, Xian Li, Graham Neubig, Yusuke Oda
Venue:
NGT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
204–210
Language:
URL:
https://aclanthology.org/2020.ngt-1.24
DOI:
10.18653/v1/2020.ngt-1.24
Bibkey:
Cite (ACL):
Chi Hu, Bei Li, Yinqiao Li, Ye Lin, Yanyang Li, Chenglong Wang, Tong Xiao, and Jingbo Zhu. 2020. The NiuTrans System for WNGT 2020 Efficiency Task. In Proceedings of the Fourth Workshop on Neural Generation and Translation, pages 204–210, Online. Association for Computational Linguistics.
Cite (Informal):
The NiuTrans System for WNGT 2020 Efficiency Task (Hu et al., NGT 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.ngt-1.24.pdf
Video:
 http://slideslive.com/38929838
Code
 niutrans/niutensor +  additional community code