Multichannel LSTM-CRF for Named Entity Recognition in Chinese Social Media

被引:7
作者
Dong, Chuanhai [1 ,2 ]
Wu, Huijia [1 ,2 ]
Zhang, Jiajun [1 ,2 ]
Zong, Chengqing [1 ,2 ,3 ]
机构
[1] Natl Lab Pattern Recognit, CASIA, Beijing, Peoples R China
[2] Univ Chinese Acad Sci, Beijing, Peoples R China
[3] CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai, Peoples R China
来源
CHINESE COMPUTATIONAL LINGUISTICS AND NATURAL LANGUAGE PROCESSING BASED ON NATURALLY ANNOTATED BIG DATA, CCL 2017 | 2017年 / 10565卷
关键词
Multichannel; Named entity recognition; Chinese social media;
D O I
10.1007/978-3-319-69005-6_17
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Named Entity Recognition (NER) is a tough task in Chinese social media due to a large portion of informal writings. Existing research uses only limited in-domain annotated data and achieves low performance. In this paper, we utilize both limited in-domain data and enough out-of-domain data using a domain adaptation method. We propose a multichannel LSTM-CRF model that employs different channels to capture general patterns, in-domain patterns and out-of-domain patterns in Chinese social media. The extensive experiments show that our model yields 9.8% improvement over previous state-of-the-art methods. We further find that a shared embedding layer is important and randomly initialized embeddings are better than the pretrained ones.
引用
收藏
页码:197 / 208
页数:12
相关论文
共 33 条
[11]  
Chang C. Y, 2016, P NAACL HLT CAL US, P400, DOI DOI 10.18653/V1/N16-1045
[12]  
Chen YF, 2010, ACL 2010: 48TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, P631
[13]  
Cherry Colin., 2015, Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, P735, DOI 10.3115/v1/ N15-1075
[14]  
Collobert R, 2011, J MACH LEARN RES, V12, P2493
[15]   Character-Based LSTM-CRF with Radical-Level Features for Chinese Named Entity Recognition [J].
Dong, Chuanhai ;
Zhang, Jiajun ;
Zong, Chengqing ;
Hattori, Masanori ;
Di, Hui .
NATURAL LANGUAGE UNDERSTANDING AND INTELLIGENT APPLICATIONS (NLPCC 2016), 2016, 10102 :239-250
[16]  
Fu G., 2005, ACM SIGKDD Explorations Newsletter, V7, P19, DOI DOI 10.1145/1089815.1089819
[17]  
Geoffrey EHinton., 2012, Improving neural networks by preventing co-adaptation of feature detectors
[18]  
Gottipati S., 2011, P EMNLP, P804
[19]  
Han Aaron L.-F, 2013, Language Processing and Intelligent Information Systems. 20th International Conference, IIS 2013. Proceedings. LNCS 7912, P57, DOI 10.1007/978-3-642-38634-3_8
[20]  
He H, 2017, 31 AAAI C ART INT