CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
An Empirical Exploration of Skip Connections for Sequential Tagging
Wu HJ(吴惠甲); Zhang JJ(张家俊); Zong CQ(宗成庆)
2016
Conference NameCOLING
Conference Date2016-12
Conference Place日本
AbstractIn this paper, we empirically explore the effects of various kinds of skip connections in stacked bidirectional LSTMs for sequential tagging. We investigate three kinds of skip connections connecting to LSTM cells: (a) skip connections to the gates, (b) skip connections to the internal states and (c) skip connections to the cell outputs. We present comprehensive experiments showing that skip connections to cell outputs outperform the remaining two. Furthermore, we observe that using gated identity functions as skip mappings works pretty well. Based on this novel skip connections, we successfully train deep stacked bidirectional LSTM models and obtain state-of-the-art results on CCG supertagging and comparable results on POS tagging.
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/14508
Collection模式识别国家重点实验室_自然语言处理
Affiliation中国科学院自动化研究所
Recommended Citation
GB/T 7714
Wu HJ,Zhang JJ,Zong CQ. An Empirical Exploration of Skip Connections for Sequential Tagging[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
COLING-16.pdf(223KB)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
[Wu HJ(吴惠甲)]'s Articles
[Zhang JJ(张家俊)]'s Articles
[Zong CQ(宗成庆)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wu HJ(吴惠甲)]'s Articles
[Zhang JJ(张家俊)]'s Articles
[Zong CQ(宗成庆)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wu HJ(吴惠甲)]'s Articles
[Zhang JJ(张家俊)]'s Articles
[Zong CQ(宗成庆)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: COLING-16.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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