CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
Shortcut Sequence Tagging
Wu, Huijia; Zhang, Jiajun; Zong, Chengqing
Conference NameNLPCC-2017
Conference Date2017-11.8-12
Conference PlaceDalian, China

Deep stacked RNNs are usually hard to train. Recent studies have shown that shortcut connections across different RNN layers bring substantially faster convergence. However, shortcuts increase the computational complexity of the recurrent computations. To reduce the complexity, we propose the shortcut block, which is a refinement of the shortcut LSTM blocks. Our approach is to replace the self-connected parts (c l t) with shortcuts (h l−2 t ) in the internal states. We present extensive empirical experiments showing that this design performs better than the original shortcuts. We evaluate our method on CCG supertagging task, obtaining a 8% relatively improvement over current state-of-the-art results.

Document Type会议论文
Recommended Citation
GB/T 7714
Wu, Huijia,Zhang, Jiajun,Zong, Chengqing. Shortcut Sequence Tagging[C],2017.
Files in This Item: Download All
File Name/Size DocType Version Access License
1109.pdf(489KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wu, Huijia]'s Articles
[Zhang, Jiajun]'s Articles
[Zong, Chengqing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wu, Huijia]'s Articles
[Zhang, Jiajun]'s Articles
[Zong, Chengqing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wu, Huijia]'s Articles
[Zhang, Jiajun]'s Articles
[Zong, Chengqing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 1109.pdf
Format: Adobe PDF
All comments (0)
No comment.

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