Candidate region aware nested named entity recognition

作     者：Jiang, Deng Ren, Haopeng Cai, Yi Xu, Jingyun Liu, Yanxia Leung, Ho-fung 

作者机构：South China Univ Technol Minist Educ Key Lab Big Data & Intelligent Robot Guangzhou Peoples R China South China Univ Technol Sch Software Engn Guangzhou Peoples R China Chinese Univ Hong Kong Dept Comp Sci & Engn Hong Kong Peoples R China 

出 版 物：《NEURAL NETWORKS》 (神经网络)

年 卷 期：2021年第142卷

页      面：340-350页

核心收录：

学科分类：1002[医学-临床医学] 1001[医学-基础医学(可授医学、理学学位)] 0812[工学-计算机科学与技术（可授工学、理学学位）] 10[医学] 

基　　金：National Natural Science Foundation of China National Key Research and Development Program of China Fundamental Research Funds for the Central Universities, SCUT [2017ZD048, D2182480] Science and Technology Programs of Guangzhou [201704030076, 201802010027, 201902010046] Hong Kong Research Grants Council [C1031-18G] Science and Technology Planning Project of Guangdong Province [2020B0101100002] 

主　　题：Named entity recognition Sequence labeling Multi-task learning 

摘      要：Named entity recognition (NER) is crucial in various natural language processing (NLP) tasks. However, the nested entities which are common in practical corpus are often ignored in most of current NER models. To extract the nested entities, two categories of models (i.e., feature-based and neural network-based approaches) are proposed. However, the feature-based models suffer from the complicated feature engineering and often heavily rely on the external resources. Discarding the heavy feature engineering, recent neural network-based methods which treat the nested NER as a classification task are designed but still suffer from the heavy class imbalance issue and the high computational cost. To solve these problems, we propose a neural multi-task model with two modules: Binary Sequence Labeling and Candidate Region Classification to extract the nested entities. Extensive experiments are conducted on the public datasets. Comparing with recent neural network-based approaches, our proposed model achieves the better performance and obtains the higher efficiency. (C) 2021 Published by Elsevier Ltd.