Jinshan Zhang
ABSTRACT
The entity recognition status of Chinese medical literature is introduced in the paper. On the foundation, we propose a method based on fusion-feature to solve problems of medical named entity recognition. Then, the BiLSTM-CRF model is constructed by combining the Conditional Random Field (CRF) of Bidirectional Long Short-Term Memory (BiLSTM) network. It is used to obtain long-distance context information and label entity types. We use Word2vec to build the embedding layer. The characters and words in the sentence are converted into dense vectors with fusing external dictionary features. The results show that compared with using traditional CRF model, the method based on fusion-feature BiLSTM-CRF has better effect, and the F-measure is increased by 7.51%.
- Zhang Mingtao, Han Pu. Advances in medical entity recognition research[J]. Computer Technology and Development, 2020, 30 (04): 57--62.Google Scholar
- Sun Chengjie. Research on related problems of biomedical Text Mining based on discriminant model[D]. Harbin Institute of Technology, 2008.Google Scholar
- Han pu, Liu Yizuo, Li Xiaoyan. Entity Recognition of Chinese Electronic Medical Record based on deep learning and Multi-feature Fusion[J]. Journal of Nanjing University (Natural Science), 2019, 55 (06): 942--951.Google Scholar
- Carolina Fócil-Arias, Grigori Sidorov, Alexander Gelbukh, Fernando Arce. Extracting medical events from clinical records using conditional random fields and parameter tuning for hidden Markov models[J]. Journal of Intelligent & Fuzzy Systems, 2018, 34 (05): 1--13.Google ScholarDigital Library
- Collobert R, Weston J, Bottou, Léon, et al. Natural Language Processing (almost) from Scratch[J]. Journal of Machine Learning Research, 2011, 12 (1): 2493--2537.Google ScholarDigital Library
- Wang Ruojia, Wei Siyi, Wang Jimin. Application of BILSTM-CRF model in Chinese Electronic medical Record named Entity Recognition[J]. Journal of Literature and Data, 2019, (02): 53--66.Google Scholar
- Huang Wei, Huang Jianqiao, Li Yuefeng. BiLSTM-CRF based Entity Recognition Model of Terrorism-related Information[J]. Intelligence Magazine, 2019, 38 (12): 149--156.Google Scholar
- Xia Guanghui, Li Junlian, Xing Baokun, Cui Shengnan. Research on named entity Recognition of medical diagnosis and treatment based on Chinese case report literature[J]. Journal of Medical Informatics, 2019, 40 (06): 54--59.Google Scholar
- Zhang Junfei, Bizhi Sheng, Wangjing, Wu Xiaoling. Design based on BiLSTM-CRF Chinese domain named entity recognition framework[J]. Computing Technology and Automation, 2019, 38 (03): 117--121.Google Scholar
- Jiang Yiqi, Zhao Tongzhou, Chai Yue, Gao Peidong. Sports news topic extraction method based on bilstm[J]. Journal of Wuhan University of Technology, 2020, 42 (01): 102--107Google Scholar
- Ma Sidan, Liu Dongsu. Research on text classification method based on weighted Word2vec[J]. Information Science, 2019, 37 (11): 38--42.Google Scholar
- Song Tianshu, Li Jiangyu, Zhang Qinzhe. Clustering research of personal microblog based on CBOW model[J]. Computer and Telecommunication, 2018, (04): 69--72.Google Scholar
Index Terms
- Entity Recognition of Chinese Medical Literature Based on BiLSTM-CRF and Fusion Features
Recommendations
Chinese Named Entity Recognition Based on Rules and Conditional Random Field
CSAI '18: Proceedings of the 2018 2nd International Conference on Computer Science and Artificial IntelligenceIn the era of big data, data has gradually become an important productivity driving social progress. Accelerating the development and sharing of data resources is an inherent requirement of government transformation. Named entity recognition has a wide ...
CRF-based active learning for Chinese named entity recognition
SMC'09: Proceedings of the 2009 IEEE international conference on Systems, Man and CyberneticsConditional Random Fields (CRFs) have been used for many sequence labeling tasks and got excellent results. Further, the supervised model strongly depends on the huge training data. Active learning is a different way rather than relying on a large ...
Named entity recognition from Chinese adverse drug event reports with lexical feature based BiLSTM-CRF and tri-training
Graphical abstractNamed Entities Recognition (NER) models are established to extract entities from free-text Chinese Adverse Drug Event (ADE) reports, and through which, ADR-related entities of Reasons for medication, Drugs used and ADR names ...
Highlights- Cases were manually annotated for model training.
- Named entity recognition ...
Abstract BackgroundThe Adverse Drug Event Reports (ADERs) from the spontaneous reporting system are important data sources for studying Adverse Drug Reactions (ADRs) as well as post-marketing pharmacovigilance. Apart from the ...
Comments