CASIA OpenIR  > 数字内容技术与服务研究中心  > 听觉模型与认知计算
Named Entity Recognition with Gated Convolutional Neural Networks
Wang CQ(汪春奇)1,2; Chen W(陈玮)1; Xu B(徐波)1
Conference Name第十六届全国计算语言学学术会议
Conference Date2017
Conference Place南京

Most state-of-the-art models for named entity recognition (NER) rely on recurrent neural networks (RNNs), in particular long short-term memory (LSTM). Those models learn local and global fea- tures automatically by RNNs so that hand-craft features can be dis- carded, totally or partly. Recently, convolutional neural networks (CNNs) have achieved great success on computer vision. However, for NER prob- lems, they are not well studied. In this work, we propose a novel archi- tecture for NER problems based on GCNN — CNN with gating mech- anism. Compared with RNN based NER models, our proposed model has a remarkable advantage on training efficiency. We evaluate the pro- posed model on three data sets in two significantly different languages — SIGHAN bakeoff 2006 MSRA portion for simplified Chinese NER and CityU portion for traditional Chinese NER, CoNLL 2003 shared task English portion for English NER. Our model obtains state-of-the-art performance on these three data sets.

KeywordNamed Entity Recognition Convolutional Neural Network Sequence Labeling
Document Type会议论文
Recommended Citation
GB/T 7714
Wang CQ,Chen W,Xu B. Named Entity Recognition with Gated Convolutional Neural Networks[C],2017:110-121.
Files in This Item: Download All
File Name/Size DocType Version Access License
submission.pdf(319KB)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
[Wang CQ(汪春奇)]'s Articles
[Chen W(陈玮)]'s Articles
[Xu B(徐波)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang CQ(汪春奇)]'s Articles
[Chen W(陈玮)]'s Articles
[Xu B(徐波)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang CQ(汪春奇)]'s Articles
[Chen W(陈玮)]'s Articles
[Xu B(徐波)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: submission.pdf
Format: Adobe PDF
All comments (0)
No comment.

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