Please wait a minute...
Advanced Search
数据分析与知识发现  2016, Vol. 32 Issue (12): 36-43    DOI: 10.11925/infotech.1003-3513.2016.12.05
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于深度学习的中文机构名识别研究*——一种汉字级别的循环神经网络方法
朱丹浩1,2(),杨蕾3,王东波4
1江苏警官学院图书馆 南京 210031
2南京大学计算机科学与技术系 南京 210093
3南京交通技师学院中(高)职教育处 南京 210049
4南京农业大学信息科学技术学院 南京 210095
Recognizing Chinese Organization Names Based on Deep Learning: A Recurrent Network Model
Danhao Zhu1,2(),Lei Yang3,Dongbo Wang4
1Library of Jiangsu Police Institute, Nanjing 210031, China
2Department of Computer Science and Technology, Nanjing University, Nanjing 210093, China
3Department of High Education, College of Nanjing Traffic Technician, Nanjing 210049, China
4College of Information Science and Technology, Nanjing Agricultural University, Nanjing 210095, China
全文: PDF(526 KB)   HTML ( 48
输出: BibTeX | EndNote (RIS)      
摘要 

目的】中文机构名结构复杂、罕见词多, 识别难度大, 对其进行正确识别对于信息抽取、信息检索、知识挖掘和机构科研评价等情报学中的后续任务意义重大。【方法】基于深度学习的循环神经网络(Recurrent Neural Network, RNN)方法, 面向中文汉字和词的特点, 重新定义了机构名标注的输入和输出, 提出汉字级别的循环网络标注模型。【结果】以词级别的循环神经网络方法为基准, 本文提出的字级别模型在中文机构名识别的准确率、召回率和F值均有明显提高, 其中F值提高了1.54%。在包含罕见词时提高更为明显, F值提高了11.05%。【局限】在解码时直接使用了贪心策略, 易于陷入局部最优, 如果使用条件随机场算法进行建模可能获取全局最优结果。【结论】本文方法构架简单, 能利用到汉字级别的特征来进行建模, 比只使用词特征取得了更好的结果。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
朱丹浩
杨蕾
王东波
关键词 机构名识别循环神经网络深度学习    
Abstract

[Objective]Chinese organization names are difficult to be recognized by computers due to their complex structures and using of rare words. Successful recognition of these names plays significant roles in information extraction and retrieval, knowledge mining as well as institution research evaluation. [Methods] First, we redefined the input and output of organization names based on recurrent neural network method and nature of Chinese words or phrases. Second, we proposed a new model at the word level. [Results] Compared to the recurrent network models at the phrase level, the proposed method significantly improved the precision, recall and F value. Among them, the F value increased 1.54%. For organization names with rare words, the F value increased by 11.05%. [Limitations] We adopted a greedy strategy to find the local optimal values. A conditional random field method will yield better results from the global perspective. [Conclusions] The proposed method, which uses Chinese word level features, is easy to be implemented, and could generate better results than its phrase based counterparts.

Key wordsOrganization recognition    Recurrent Neural Network    Deep learning
收稿日期: 2016-08-01     
基金资助:*本文系江苏省高校哲学社会科学项目“高校危机管理案例知识库构建及知识挖掘研究”(项目编号: 2014SJB246)、江苏省警官学院“公安学术语自动抽取技术研究”(项目编号: 2015SJYZQ01)和国家自然科学基金项目“基于CSSCI的句法级汉英平行语料库构建及知识挖掘研究”(项目编号: 71303120)的研究成果之一
引用本文:   
朱丹浩, 杨蕾, 王东波. 基于深度学习的中文机构名识别研究*——一种汉字级别的循环神经网络方法[J]. 数据分析与知识发现, 2016, 32(12): 36-43.
Danhao Zhu, Lei Yang, Dongbo Wang. Recognizing Chinese Organization Names Based on Deep Learning: A Recurrent Network Model. Data Analysis and Knowledge Discovery, DOI:10.11925/infotech.1003-3513.2016.12.05.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.1003-3513.2016.12.05
[1] 沈嘉懿, 李芳, 徐飞玉, 等. 中文组织机构名称与简称的识别[J]. 中文信息学报, 2007, 21(6): 17-21.
[1] (Shen Jiayi, Li Fang, Xu Feiyu, et al.Recognition of Chinese Organization Names and Abbreviations[J]. Journal of Chinese Information Processing, 2007, 21(6): 17-21.)
[2] 周俊生, 戴新宇, 尹存燕, 等. 基于层叠条件随机场模型的中文机构名自动识别[J]. 电子学报, 2006, 34(5): 804-809.
[2] (Zhou Junsheng, Dai Xinyu, Yin Cunyan, et al.Automatic Recognition of Chinese Organization Name Based on Cascaded Conditional Random Fields[J]. Acta Electronica Sinica, 2006, 34(5): 804-809.)
[3] 黄德根, 李泽中, 万如. 基于SVM和CRF的双层模型中文机构名识别[J]. 大连理工大学学报, 2010, 50(5): 782-787.
[3] (Huang Degen, Li Zezhong, Wan Ru.Chinese Organization Name Recognition Using Cascaded Model Based on SVM and CRF[J]. Journal of Dalian University of Technology, 2010, 50(5): 782-787.)
[4] 滕青青, 吉久明, 郑荣廷, 等.基于文献的中文命名实体识别算法适用性分析研究[J]. 情报杂志, 2010, 29(9): 157-161.
[4] (Teng Qingqing, Ji Jiuming, Zheng Yongting, et al.Applicability Analysis of Chinese Named Entity Recognition Method Based on Literatures[J]. Journal of Intelligence, 2010, 29(9): 157-161.)
[5] Huang Z, Xu W, Yu K.Bidirectional LSTM-CRF Models for Sequence Tagging [OL]. arXiv Preprint.arXiv: 1508.01991.
[6] Chen X, Qiu X, Zhu C, et al.Gated Recursive Neural Network for Chinese Word Segmentation [C]. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.2015: 1744-1753.
[7] Chen X, Xu L, Liu Z, et al.Joint Learning of Character and Word Embeddings [C]. In: Proceedings of the 24th International Conference on Artificial Intelligence. 2015: 1236-1242.
[8] Sun Y, Lin L, Yang N, et al.Radical-enhanced Chinese Character Embedding [C]. In: Proceedings of the International Conference on Neural Information Processing. Springer International Publishing, 2014: 279-286.
[9] 孙镇, 王惠临. 命名实体识别研究进展综述[J]. 现代图书情报技术, 2010(6): 42-47.
[9] (Sun Zhen, Wang Huilin.Overview on the Advance of the Research on Named Entity Recognition[J]. New Technology of Library and Information Service, 2010(6): 42-47.)
[10] 潘正高. 基于规则和统计相结合的中文命名实体识别研究[J]. 情报科学, 2012, 30(5): 708-712.
[10] (Pan Zhenggao.Research on the Recognition of Chinese Named Entity Based on Rules and Statistics[J]. Information Science, 2012, 30(5): 708-712.)
[11] 陆伟, 鞠源, 张晓娟, 等. 产品命名实体特征选择与识别研究[J]. 图书情报知识, 2012(3): 4-12.
[11] (Lu Wei, Ju Yuan, Zhang Xiaojuan, et al.Research on Product Named Entity Feature Selection and Recognition[J]. Document, Information & Knowledge, 2012(3): 4-12.)
[12] 吴丹, 何大庆, 陆伟. 跨语言信息检索中的命名实体识别与翻译[J]. 图书情报知识, 2012(3): 13-19.
[12] (Wu Dan, He Daqing, Lu Wei.The Extraction and Translation of Named Entity in Cross Language Information Retrieval[J]. Document, Information & Knowledge, 2012(3): 13-19.)
[13] 王文龙, 王东波. 面向项目申请书的命名实体抽取模型构建研究[J]. 情报资料工作, 2015(1): 30-34.
[13] (Wang Wenlong, Wang Dongbo.Project Application-oriented Named Entity Extraction Model Construction[J]. Information and Documentation Services, 2015(1): 30-34.)
[14] 陈锋, 翟羽佳, 王芳. 基于条件随机场的学术期刊中理论的自动识别方法[J]. 图书情报工作, 2016, 60(2): 122-128.
[14] (Chen Feng, Zhai Yujia, Wang Fang.Automatic Theory Recognition in Academic Journals Based on CRF[J]. Library and Information Service, 2016, 60(2): 122-128.)
[15] 俞鸿魁, 张华平, 刘群.基于角色标注的中文机构名识别[C]. 见: 第 20 届东方语言计算机处理国际会议论文集. 2003: 79-87.
[15] (Yu Hongkui, Zhang Huaping, Liu Qun.Recognition of Chinese Organization Name Based on Role Tagging [C]. In: Proceedings of the 20th International Conference on Computer Processing of Oriental Languages. 2003: 79-87.)
[16] 关晓炟, 吕学强, 李卓, 等. 用户查询日志中的中文机构名识别[J]. 现代图书情报技术, 2014(1): 72-78.
[16] (Guan Xiaoda, Lv Xueqiang, Li Zhuo, et al.Chinese Organization Name Recognition in User Query Log[J]. New Technology of Library and Information Service, 2014(1): 72-78.)
[17] Huang Z, Xu W, Yu K.Bidirectional LSTM-CRF Models for Sequence Tagging [OL]. arXiv: 1508.01991.
[18] Ma X, Hovy E.End-to-End Sequence Labeling via Bi-directional LSTM-CNNs-CRF [OL]. arXiv Preprint. arXiv: 1603.01354.
[19] Hochreiter S, Schmidhuber J.Long Short-term Memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[20] Sutskever I, Vinyals O, Le Q V.Sequence to Sequence Learning with Neural Networks [A]. //Advances in Neural Information Processing Systems[M]. 2014: 3104-3112.
[21] Pascanu R, Mikolov T, Bengio Y.On the Difficulty of Training Recurrent Neural Networks[J]. Journal of Machine Learning Research, 2013, 28(3): 1310-1318.
[22] Srivastava N, Hinton G, Krizhevsky A, et al.Dropout: A Simple Way to Prevent Neural Networks from Overfitting[J]. Journal of Machine Learning Research, 2014, 15(1): 1929-1958.
[1] 张梦吉,杜婉钰,郑楠. 引入新闻短文本的个股走势预测模型[J]. 数据分析与知识发现, 2019, 3(5): 11-18.
[2] 裴晶晶,乐小虬. 篇章级并列关系文本块识别方法研究[J]. 数据分析与知识发现, 2019, 3(5): 51-56.
[3] 余丽,钱力,付常雷,赵华茗. 基于深度学习的文本中细粒度知识元抽取方法研究*[J]. 数据分析与知识发现, 2019, 3(1): 38-45.
[4] 付常雷,钱力,张华平,赵华茗,谢靖. 基于深度学习的创新主题智能挖掘算法研究*[J]. 数据分析与知识发现, 2019, 3(1): 46-54.
[5] 余本功,张培行,许庆堂. 基于F-BiGRU情感分析的产品选择方法*[J]. 数据分析与知识发现, 2018, 2(9): 22-30.
[6] 陆伟,罗梦奇,丁恒,李信. 深度学习图像标注与用户标注比较研究*[J]. 数据分析与知识发现, 2018, 2(5): 1-10.
[7] 冯国明,张晓冬,刘素辉. 基于CapsNet的中文文本分类研究*[J]. 数据分析与知识发现, 2018, 2(12): 68-76.
[8] 肖延辉,王欣,冯文刚,田华伟,吴绍忠,李丽华. 基于长短记忆型卷积神经网络的犯罪地理位置预测方法*[J]. 数据分析与知识发现, 2018, 2(10): 15-20.
[9] 冯文刚,黄静. 基于深度学习的民航安检和航班预警研究*[J]. 数据分析与知识发现, 2018, 2(10): 46-53.
[10] 胡家珩,岑咏华,吴承尧. 基于深度学习的领域情感词典自动构建*——以金融领域为例[J]. 数据分析与知识发现, 2018, 2(10): 95-102.
[11] 邓三鸿,傅余洋子,王昊. 基于LSTM模型的中文图书多标签分类研究*[J]. 数据分析与知识发现, 2017, 1(7): 52-60.
[12] 张李义,刘畅. 结合深度置信网络和模糊集的虚假交易识别研究[J]. 现代图书情报技术, 2016, 32(1): 32-39.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn