Named Entity Recognition with Gated Convolutional Neural Networks

摘要：

　　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.

作者: Chunqi Wang Wei Chen Bo Xu

作者单位: University of Chinese Academy of Sciences;Institute of Automation,Chinese Academy of Sciences Institute of Automation,Chinese Academy of Sciences

会议类型: 国内会议

会议名称: 第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会

会议地点: 南京

会议语种:英文

页码: 1-12

在线出版日期: 2017-10-13（万方平台首次上网日期，不代表论文的发表时间）