融合CRF与规则的老挝语军事领域命名实体识别方法

doi:10.19678/j.issn.1000-3428.0055363

计算机工程 ›› 2020, Vol. 46 ›› Issue (8): 297-304. doi: 10.19678/j.issn.1000-3428.0055363

融合CRF与规则的老挝语军事领域命名实体识别方法

何阳宇¹, 晏雷², 易绵竹¹, 李宏欣^1,3

1. 中国人民解放军战略支援部队信息工程大学(洛阳校区), 河南洛阳 471003;
2. 昆明理工大学信息工程与自动化学院, 昆明 650500;
3. 密码科学技术国家重点实验室, 北京 100878

收稿日期:2019-07-02 修回日期:2019-08-21 发布日期:2019-09-02
作者简介:何阳宇(1992-),男,博士研究生,主研方向为自然语言处理、知识图谱;晏雷,硕士研究生;易绵竹,教授、博士生导师;李宏欣,讲师、博士。
基金资助:
国家自然科学基金（61701539）；密码科学技术国家重点实验室开放课题（MMKFKT201825）；国防科技创新特区项目。

Named Entitiy Recognition Method for Laotian in Military Field Combining CRF and Rules

HE Yangyu¹, YAN Lei², YI Mianzhu¹, LI Hongxin^1,3

1. PLA Strategic Support Force Information Engineering University(Luoyang Campus), Luoyang, Henan 471003, China;
2. College of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China;
3. State Key Laboratory of Cryptology, Beijing 100878, China

Received:2019-07-02 Revised:2019-08-21 Published:2019-09-02

摘要/Abstract

摘要： 针对老挝语军事领域命名实体识别存在的规则制定不准确、覆盖不全等问题，提出一种融合条件随机场与规则的识别方法。通过分析老挝语语言和领域文本特点，选取词、词性、通名、指界词和词典等原子特征构建组合特征模板，在自建标注语料上训练条件随机场模型，并利用测试语料进行测试。为识别错例，加入能够表达语言确定性的规则进行后处理，以提升识别性能。实验结果表明，该方法总体准确率、召回率和F测度值分别达到91.49%、90.96%和91.22%，可有效提高老挝语军事领域命名实体识别效果。

关键词: 命名实体识别, 军事领域, 老挝语, 条件随机场, 信息抽取

Abstract: To address the problems of inaccurate formulation and incomplete coverage of existing methods for Laotian Named Entity Recognition(NER) in the military field,this paper proposes a method combining Conditional Random Field(CRF) and rules.By analyzing the characteristics of Laotian and domain texts,the method selects the atomic features such as the word,the part of speech,the general name,the boundary word and the dictionary to construct a combined feature template.The CRF model is trained on the self-built tagged corpus,and tested by using the test corpus.To identify wrong examples,it adds rules that can express language certainty for post-processing to improve recognition performance.Experimental results show that the final overall accuracy,recall rate and F measures of this method reach 91.49%,90.96% and 91.22% respectively,effectively improve the Laotian Named Entity Recognition(NER) in military field.

Key words: Named Entity Recognition(NER), military field, Laotian, Conditional Random Field(CRF), Information Extraction(IE)

中图分类号:

TP391

何阳宇, 晏雷, 易绵竹, 李宏欣. 融合CRF与规则的老挝语军事领域命名实体识别方法[J]. 计算机工程, 2020, 46(8): 297-304.

HE Yangyu, YAN Lei, YI Mianzhu, LI Hongxin. Named Entitiy Recognition Method for Laotian in Military Field Combining CRF and Rules[J]. Computer Engineering, 2020, 46(8): 297-304.

http://www.ecice06.com/CN/Y2020/V46/I8/297

图/表 13

20200819141314

20200819141317

20200819141320

20200819141322

20200819141325

20200819141328

20200819141331

20200819141334

20200819141338

20200819141342

20200819141345

20200819141347

20200819141350

参考文献

[1] JURAFSKY D,MARTIN J H.Speech and language processing[M].2nd ed.FENG Zhiwei,SUN Le,Translated.Beijing:Publishing House of Electronics Industry,2018.(in Chinese) JURAFSKY D,MARTIN J H.自然语言处理综论[M].2版.冯志伟,孙乐,译.北京:电子工业出版社,2018.
[2] HE Yangyu,YI Mianzhu,JIA Huixin,et al.A survey of Lao named entity recognition[J].Modern Linguistics,2018,6(3):449-461.(in Chinese)何阳宇,易绵竹,贾惠心,等.老挝语命名实体识别研究综述[J].现代语言学,2018,6(3):449-461.
[3] MAIHEMUTI Maimaiti,KAHAERJIANG Abiderexiti,AISHAN Wumaier,et al.Uyghur location names recognition based on conditional random fields and rules[J].Journal of Chinese Information Processing,2017,31(6):110-118.(in Chinese)买合木提·买买提,卡哈尔江·阿比的热西提,艾山·吾买尔,等.CRF与规则相结合的维吾尔文地名识别研究[J].中文信息学报,2017,31(6):110-118.
[4] BIKEL D M,SCHWARTZ R,WEISCHEDEL R M.An algorithm that learns what's in a name[J].Machine Learning,1999,34(1/2/3):211-231.
[5] LAFFERTY J D,MCCALLUM A,PEREIRA F C N.Conditional random fields:probabilistic models for segmenting and labeling sequence data[C]//Proceedings of the 18th International Conference on Machine Learning.New York,USA:ACM Press,2001:282-289.
[6] Special Committee on Language and Knowledge Computing of the Chinese Information Society of China.Knowledge graph development report(2018)[EB/OL].(2018-08-18)[2019-02-15].http://cips-upload.bj.bcebos.com/KGDevReport2018.pdf.(in Chinese)中国中文信息学会语言与知识计算专委会.知识图谱发展报告(2018)[EB/OL].(2018-08-18)[2019-02-15].http://cips-upload.bj.bcebos.com/KGDevReport2018.pdf.
[7] LAMPLE G,BALLESTEROS M,SUBRAMANIAN S,et al.Neural architectures for named entity recognition[C]//Proceedings of NAACL-HLT'16.Sacramento,USA:Association for Computational Linguistics,2016:260-270.
[8] XU M,JIANG H,WATCHARAWITTAYAKUL S.A local detection approach for named entity recognition and mention detection[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.Vancouver,Canada:[s.n.],2017:1237-1247.
[9] WANG Hongbin,GAO Hongkui,SHEN Qiang,et al.Thai language names,place names and organization names entity recognition[J].Journal of System Simulation,2019,31(5):1010-1018.(in Chinese)王红斌,郜洪奎,沈强,等.泰语人名、地名、机构名实体识别研究[J].系统仿真学报,2019,31(5):1010-1018.
[10] SRITHIRATH A,SERESANGTAKUL P.A hybrid approach to Lao word segmentation using longest syllable level matching with named entities recognition[C]//Proceedings of International Conference on Electrical Engineering/Electronics,Computer,Telecommunications and Information Technology.Krabi,Thailand:[s.n.],2013:1-5.
[11] YANG Mengjie.Research on Lao language named entity recognition method[D].Kunming:Kunming University of Science and Technology,2016.(in Chinese)杨梦杰.老挝语命名实体识别方法的研究[D].昆明:昆明理工大学,2016.
[12] DUAN Shaopeng.Research on Lao language entity recognition[D].Kunming:Kunming University of Science and Technology,2017.(in Chinese)段韶鹏.老挝语命名实体识别研究[D].昆明:昆明理工大学,2017.
[13] HAN Rui.Research on Chinese-Lao language bilingual named entity recognition and alignment method[D].Kunming:Kunming University of Science and Technology,2018.(in Chinese)韩锐.汉老双语命名实体识别及对齐方法研究[D].昆明:昆明理工大学,2018.
[14] HUANG Yuquan.Research on identification of Lao language names,places and institutions[D].Kunming:Kunming University of Science and Technology,2018.(in Chinese)黄于权.老挝语人名、地名及机构名识别研究[D].昆明:昆明理工大学,2018.
[15] LEI Shujie,XING Fukun.Types and patterns of the English names of military weapons and equipments[J].China Terminology,2019,21(1):14-20.(in Chinese)雷树杰,邢富坤.英文武器装备名的构成类型与构造模式研究[J].中国科技术语,2019,21(1):14-20.
[16] MCCALLUM A,LI W.Early results for named entity recognition with conditional random fields,feature induction and web-enhanced lexicons[C]//Proceedings of the 7th Conference on Natural Language Learning.Edmonton,Canada:[s.n.],2003:188-191.
[17] ZONG Chengqing.Statistical natural language processing[M].2nd ed.Beijing:Tsinghua University Press,2013.(in Chinese)宗成庆.统计自然语言处理[M].2版.北京:清华大学出版社,2013.
[18] WALLACH H M.Conditional random fields:an introduction[EB/OL].(2004-02-24)[2019-04-26].http://repository.upenn.edu/cis_reports/22.
[19] SU Tingting.A study of the name culture of Lao Lao people[D].Nanning:Guangxi University for Nationalities,2015.(in Chinese)苏婷婷.老挝佬族姓名文化研究[D].南宁:广西民族大学,2015.
[20] HUANG Yong,QIN Hailun.Lao-Chinese language Chinese-Lao language military dictionary[M].Beijing:Yi Wen Publishing Military,2009.(in Chinese)黄勇,覃海伦.老汉-汉老军事词典[M].北京:军事谊文出版社,2009.
[21] Lao National Bureau of Statistics.2017 statistical yearbook[M].Vientiane,Lao:Lao National Bureau of Statistics,2018.(in Chinese)老挝国家统计局.2017统计年鉴[M].万象,老挝:老挝国家统计局,2018.
[22] WU Hui,LÜ Li,YU Bihui.Chinese named entity recognition based on transfer learning and BiLSTM-CRF[J].Journal of Chinese Computer Systems,2019,40(6):1142-1147.(in Chinese)武惠,吕立,于碧辉.基于迁移学习和BiLSTM-CRF的中文命名实体识别[J].小型微型计算机系统,2019,40(6):1142-1147.
[23] ZHONG Zhinong,LIU Fangchi,WU Ye,et al.Chinese named entity recognition combined active learning with self-training[J].Journal of National University of Defense Technology,2014,36(4):82-88.(in Chinese)钟志农,刘方驰,吴烨,等.主动学习与自学习的中文命名实体识别[J].国防科技大学学报,2014,36(4):82-88.

选择文件类型/文献管理软件名称

选择包含的内容

融合CRF与规则的老挝语军事领域命名实体识别方法

Named Entitiy Recognition Method for Laotian in Military Field Combining CRF and Rules

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	杨长沛, 廖列法. 基于门控空洞卷积特征融合的中文命名实体识别[J]. 计算机工程, 2023, 49(8): 85-95.
[2]	张家熔, 苑津莎, 许珈宁, 罗志宏. 基于多元信息嵌入与协同神经网络的力学实体识别算法[J]. 计算机工程, 2023, 49(7): 125-134.
[3]	陈明, 刘蓉, 张晔. 基于多重注意力机制的中文医疗实体识别[J]. 计算机工程, 2023, 49(6): 314-320.
[4]	毛亮, 赵林均, 余敦辉, 孙斌. 基于知识蒸馏的企业命名实体识别模型[J]. 计算机工程, 2023, 49(5): 90-96.
[5]	朱红, 牛浩然, 朱彤. 基于字词融合与对抗训练的行业人物实体识别[J]. 计算机工程, 2023, 49(5): 56-62.
[6]	衡红军, 苗菁. 语义与句法信息加强的二元标记实体关系联合抽取[J]. 计算机工程, 2023, 49(4): 77-84.
[7]	李晓腾, 张盼盼, 勾智楠, 高凯. 基于多任务学习的多模态命名实体识别方法[J]. 计算机工程, 2023, 49(4): 114-119.
[8]	廖列法, 谢树松. 基于注意力机制特征融合的中文命名实体识别[J]. 计算机工程, 2023, 49(4): 256-262.
[9]	连艺谋, 张英俊, 谢斌红. 用于嵌套命名实体识别的边界强化分类模型[J]. 计算机工程, 2022, 48(8): 313-320.
[10]	司逸晨, 管有庆. 基于Transformer编码器的中文命名实体识别模型[J]. 计算机工程, 2022, 48(7): 66-72.
[11]	李军怀, 陈苗苗, 王怀军, 崔颖安, 张爱华. 基于ALBERT-BGRU-CRF的中文命名实体识别方法[J]. 计算机工程, 2022, 48(6): 89-94,106.
[12]	张吉祥, 张祥森, 武长旭, 赵增顺. 知识图谱构建技术综述[J]. 计算机工程, 2022, 48(3): 23-37.
[13]	崔丽平, 古丽拉·阿东别克, 王智悦. 基于有向图模型的旅游领域命名实体识别[J]. 计算机工程, 2022, 48(2): 306-313.
[14]	廖涛, 黄荣梅, 张顺香, 段松松. 基于交互式特征融合的嵌套命名实体识别[J]. 计算机工程, 2022, 48(12): 119-126,133.
[15]	史占堂, 马玉鹏, 赵凡, 马博. 基于CNN‐Head Transformer编码器的中文命名实体识别[J]. 计算机工程, 2022, 48(10): 73-80.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

融合CRF与规则的老挝语军事领域命名实体识别方法

Named Entitiy Recognition Method for Laotian in Military Field Combining CRF and Rules

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献

相关文章 15

编辑推荐

Metrics

本文评价