CASIA OpenIR  > 类脑智能研究中心  > 神经计算及脑机交互
Towards Compact and Fast Neural Machine Translation Using a Combined Method
Xiaowei Zhang1,2; Wei Chen1; Feng Wang1,2; Shuang Xu1; Bo Xu1
2017-09
Conference NameThe 2017 Conference on Empirical Methods on Natural Language Processing
Pages1475–1481
Conference Date2017-9
Conference Place丹麦哥本哈根
AbstractNeural Machine Translation (NMT) lays intensive burden on computation and
memory cost. It is a challenge to deploy NMT models on the devices with limited computation and memory budgets. This paper presents a four stage pipeline to
compress model and speed up the decoding for NMT. Our method first introduces
a compact architecture based on convolutional encoder and weight shared embeddings. Then weight pruning is applied to obtain a sparse model. Next, we propose a fast sequence interpolation approach which enables the greedy decoding to achieve performance on par with the beam search. Hence, the time-consuming beam search can be replaced by simple
greedy decoding. Finally, vocabulary selection is used to reduce the computation
of softmax layer. Our final model achieves 10
× speedup, 17× parameters reduction,
<35MB storage size and comparable performance compared to the baseline model.

KeywordMachine Translation Neural Network Model Compression Decoding Speedup
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/21185
Collection类脑智能研究中心_神经计算及脑机交互
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Xiaowei Zhang,Wei Chen,Feng Wang,et al. Towards Compact and Fast Neural Machine Translation Using a Combined Method[C],2017:1475–1481.
Files in This Item: Download All
File Name/Size DocType Version Access License
Towards Compact and (257KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xiaowei Zhang]'s Articles
[Wei Chen]'s Articles
[Feng Wang]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xiaowei Zhang]'s Articles
[Wei Chen]'s Articles
[Feng Wang]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xiaowei Zhang]'s Articles
[Wei Chen]'s Articles
[Feng Wang]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Towards Compact and Fast Neural Machine Translation Using a Combined Method.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.