您的位置：山东大学 -> 科技期刊社 -> 《山东大学学报（工学版）》

山东大学学报 (工学版) ›› 2023, Vol. 53 ›› Issue (2): 70-76.doi: 10.6040/j.issn.1672-3961.0.2022.086

• • 上一篇    下一篇

基于Affix-Attention的命名实体识别语义补充方法

宋佳芮1,2,陈艳平1,2*,王凯1,2,黄瑞章1,2,秦永彬1,2   

  1. 1.公共大数据国家重点实验室, 贵州 贵阳 550025;2.贵州大学计算机科学与技术学院, 贵州 贵阳 550025
  • 收稿日期:2022-03-04 出版日期:2023-04-22 发布日期:2023-04-21
  • 作者简介:宋佳芮(1999— ),女,山西大同人,硕士研究生,主要研究方向为自然语言处理. E-mail:gs.jrsong20@gzu.edu.cn. *通信作者简介:陈艳平(1980— ),男,贵州安顺人,教授,博士,主要研究方向为自然语言处理. E-mail:Ypench@gmail.com
  • 基金资助:
    国家自然科学基金资助项目(62166007)

Semantic supplement method for named entity recognition based on Affix-Attention

SONG Jiarui1,2, CHEN Yanping1,2*, WANG Kai1,2, HUANG Ruizhang1,2, QIN Yongbin1,2   

  1. 1. State Key Laboratory of Public Big Data, Guiyang 550025, Guizhou, China;
    2. College of Computer Science and Technology, Guizhou University, Guiyang 550025, Guizhou, China
  • Received:2022-03-04 Online:2023-04-22 Published:2023-04-21

PDF (PC)

336

摘要： 针对现有命名实体识别方法存在的语义信息获取不全面问题,提出基于Affix-Attention的命名实体识别语义补充方法。将句子和句子中每个单词对应的词缀输入到编码层,使用Bi-LSTM提取上下文特征。在编码层设计特征融合模块、建模文本特征与词缀特征的对应关系,使用Affix-Attention同时关注文本信息和词缀信息进行语义补充。解码层使用CRF层得到目标序列。在生物医学领域的JNLPBA-2004和BC2GM基准数据集上的试验结果综合评价指标F1达到81.73%、84.73%;在公共数据集CONLL-2003中试验结果综合评价指标F1达到91.35%。试验结果表明,本研究方法能够有效获取词的内部语义特征,融合文本信息和词缀信息,达到语义补充的效果,提升命名实体识别的性能。

关键词: 命名实体识别, 语义补充, 注意力机制, 特征融合, 深度学习

中图分类号: 

  • TP301
[1] 刘浏, 王东波. 命名实体识别研究综述[J]. 情报学报, 2018, 37(3): 329-340. LIU Liu, WANG Dongbo. A review of research on named entity recognition[J]. Journal of Information, 2018, 37(3): 329-340.
[2] 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. SUN Zhen, WANG Huilin. A review of the research progress of named entity recognition[J]. Modern Library and Lnformation Technology, 2010(6): 42-47.
[3] 江千军, 桂前进, 王磊,等. 命名实体识别技术研究进展综述[J]. 电力信息与通信技术, 2022, 20(2): 15-24 JIANG Qianjun, GUI Qianjin, WANG Lei, et al. A review of the research progress of named entity recognition technology[J] Power Information and Communication Technology, 2022, 20(2): 15-24.
[4] CHITICARIU L, KRISHNAMURTHY R, LI Y, et al. Domain adaptation of rule-based annotators for named-entity recognition tasks[C] //Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing. Piscataway, USA: IEEE Computer Society, 2010: 1002-1012.
[5] SHEN D, ZHANG J, ZHOU G, et al. Effective adaptation of hidden markov model-based named entity recognizerfor biomedical domain[C] //Proceedings of the ACL 2003 Workshop on Natural Language Processing in Biomedicine. Sapporo, Japan: ACL, 2003: 49-56.
[6] ZHANG J, SHEN D, ZHOU G, et al. Enhancing hmm-based biomedical named entity recognition by studying special phenomena[J]. Journal of Biomedical Informatics, 2004, 37(6): 411-422.
[7] HUANG Z, XU W, YU K. Bidirectional LSTM-CRF models for sequence tagging[EB/OL].(2015-08-09)[2021-08-07]. https://arxiv.org/pdf/1508.01991.
[8] SANG E F, DE Meulder F. Introduction to the CoNLL-2003 shared task: language-independent name dentity recognition[EB/OL].(2003-01-05)[2021-09-12].http://www.ling.helsinki.fi/kit/2008s/clt350/docs/CoNLL-2003-Entities.
[9] JU M, MIWA M, ANANIADOU S. A neural layered model for nested named entity recognition[C] //Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Volume 1(Long Papers). New Orleans, Louisiana: ACL, 2018: 1446-1459.
[10] SMITH L, TANABE L K, KUO C J, et al. Overview of BioCreative II gene mention recognition[J]. Genome Biology, 2008, 9(2): 1-19.
[11] SETTLES B. Biomedical named entity recognition using conditional random fields and rich feature sets[C] //Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications(NLPBA/BioNLP). Geneva, Switzerland: [s.n.] , 2004: 107-110.
[12] WANG X, YANG C, GUAN R. A comparative study for biomedical named entity recognition[J]. International Journal of Machine Learning and Cybernetics, 2018, 9(3): 373-382.
[13] ZHOU G D, SU J. Exploring deep knowledge resources in biomedical name recognition[C] //Proceedings of the International Joint: Workshop on Natural Language Processing in Biomedicine and its Applications(NLPBA/BioNLP). Geneva, Switzerland: [s.n.] , 2004: 99-102.
[14] LIAO Z, WU H. Biomedical named entity recognition based on skip-chain Crfs[C] //2012 International Conference on Industrial Control and Electronics Engin-eering. Piscataway, USA: IEEE Computer Society, 2012: 1495-1498.
[15] TANG B, CAO H, WANG X, et al. Evaluating word representation features in biomedical named entity recognition tasks[J]. BioMed Research International, 2014: 1-6.
[16] CHANG F X, GUO J, XU W R, et al. Application of word embeddings in biomedical named entity recognition tasks[J]. Journal of Digital Information Management, 2015, 13(5): 321-327.
[17] YAO L, LIU H, LIU Y, et al. Biomedical named entity recognition based on deep neutral network[J]. Int J Hybrid Inf Technol, 2015, 8(8): 279-288.
[18] LI L, JIN L, JIANG Y, et al. Recognizing biomedical named entities based on the sentence vector/twin word embedding conditioned bidirectional LSTM[C] // Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. Yantai, China: Springer International Publishing, 2016: 165-176.
[19] LI L, GUO Y K. Biomedical named entity recognition with CNN-BLSTM-CRF[J]. Journal of Chinese Information Processing, 2018, 32(1): 116-122.
[20] NING G, BAI Y. Biomedical named entity recognition based on Glove-BLSTM-CRF model[J]. Journal of Computational Methods in Sciences and Engineering, 2021, 21(1), 125-133.
[21] XU Y, HUANG H, FENG C, et al. A supervised multi-head self-attention network for nested named entity recognition[C] //Proceedings of the AAAI Conference on Artificial Intelligence. New Orleans, Louisiana: ACL, 2021, 35(16): 14185-14193.
[22] LIU T, YAO J G, LIN C Y. Towards improving neural named entity recognition with gazetteers[C] //Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy: ACL, 2019: 5301-5307.
[23] LE A, MORITA H, IWAKURA T. Learning entity-likeness with multiple approximate matches for biomedical NER[C] //Proceedings of the International Conference on Recent Advances in Natural Language Processing(RANLP 2021).[S.l.] : [s.n.] ,2021: 1040-1049.
[24] KURU O, CAN O A, YURET D. Char NER: Character-level named entity recognition[C] // Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers. Osaka, Japan: The COLING 2016 Organizing Committee, 2016: 911-921.
[25] SHEN Y, YUN H, LIPTON Z C, et al. Deep active learning for named entity recognition[EB/OL].(2018-02-04)[2021-09-10].https://arxiv.org/pdf/1707.05928.
[26] COLLOBERT R, WESTON J, BOTTOU L, et al. Natural language processing(almost)from scratch[J]. Journal of Machine Learning Research, 2011, 12(ARTICLE):2493-2537.
[27] STRUBELL E, VERGA P, BELANGER D, et al. Fast and accurate entity recognition with iterated dilated convolutions[EB/OL].(2017-07-22)[2021-09-13]. https://arxiv.org/pdf/1702.02098.
[28] LAMPLE G, BALLESTEROS M, SUBRAMANIAN S, et al. Neural architectures for named entity recognition[EB/OL].(2016-04-07)[2021-09-13]. https://arxiv.org/pdf/1603.01360.
[29] XU M, JIANG H. A FOFE-based local detection approach for named entity recognition and mention detection[EB/OL].(2016-04-07)[2021-09-17]. https://arxiv.org/pdf/1603.01360.
[30] YANG Z, SALAKHUTDINOV R, COHEN W. Multi-task cross-lingual sequence tagging from scratch[EB/OL].(2016-08-09)[2021-09-22]. https://arxiv.org/pdf/1603.06270.
[31] MA X, HOVY E. End-to-end sequence labeling via bi-directional lstm-cnns-crf[EB/OL].(2016-05-29)[2021-09-25]. https://arxiv.org/pdf/1603.01354.
[1] 王禹鸥,苑迎春,何振学,何晨. 融合多特征和多头自注意力机制的高校学业命名实体识别[J]. 山东大学学报 (工学版), 2025, 55(6): 35-44.
[2] 李常刚,李宝亮,曹永吉,王佳颖. 人工智能在电力系统潮流计算中的应用综述及展望[J]. 山东大学学报 (工学版), 2025, 55(5): 1-17.
[3] 周遵富,张乾,石计亮,岳诗琴. 基于纹理和结构交互的人脸图像修复[J]. 山东大学学报 (工学版), 2025, 55(4): 18-28.
[4] 吴秋兰,尚素雅,张家辉,孙守鑫,张峰,周波,高峥,史文宠. 基于多尺度特征融合的马铃薯疮痂病图像语义分割方法[J]. 山东大学学报 (工学版), 2025, 55(4): 1-8.
[5] 周群颖,隋家成,张继,王洪元. 基于自监督卷积和无参数注意力机制的工业品表面缺陷检测[J]. 山东大学学报 (工学版), 2025, 55(4): 40-47.
[6] 薛冰冰,王勇,杨维浩,王川,于迪,王旭. 基于ETC收费数据的高速公路交通流数据修复及实时预测[J]. 山东大学学报 (工学版), 2025, 55(3): 58-71.
[7] 董明书,陈俐企,马川义,张珠皓,孙仁娟,管延华,庄培芝. 沥青路面内部裂缝雷达图像智能判识算法研究[J]. 山东大学学报 (工学版), 2025, 55(3): 72-79.
[8] 李丰,文益民. 融合多尺度视觉和文本语义特征的图像描述生成算法[J]. 山东大学学报 (工学版), 2025, 55(3): 80-87.
[9] 王禹鸥,苑迎春,何振学,王克俭. 改进RoBERTa、多实例学习和双重注意力机制的关系抽取方法[J]. 山东大学学报 (工学版), 2025, 55(2): 78-87.
[10] 刘全金,嵇文,胡浪涛,黄汇磊,杨瑞,李翔,高泽文,魏本征. 基于双解码器的医学图像分割模型[J]. 山东大学学报 (工学版), 2024, 54(6): 8-18.
[11] 邹正标,刘毅志,廖祝华,赵肄江. 动态交通流量预测的时空注意力图卷积网络[J]. 山东大学学报 (工学版), 2024, 54(5): 50-61.
[12] 常新功,苏敏惠,周志刚. 基于进化集成的图神经网络解释方法[J]. 山东大学学报 (工学版), 2024, 54(4): 1-12.
[13] 葛一飞,艾孜尔古丽,陈德刚. 融合数据增强和知识迁移的汉维跨语言命名实体识别[J]. 山东大学学报 (工学版), 2024, 54(4): 67-75.
[14] 索大翔,李波. 基于Gromov-Wasserstein最优传输的输电线路小目标检测方法[J]. 山东大学学报 (工学版), 2024, 54(3): 22-29.
[15] 宋辉,张轶哲,张功萱,孟元. 基于类权重和最小化预测熵的测试时集成方法[J]. 山东大学学报 (工学版), 2024, 54(3): 36-43.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 张永花,王安玲,刘福平 . 低频非均匀电磁波在导电界面的反射相角[J]. 山东大学学报(工学版), 2006, 36(2): 22 -25 .
[2] 李 侃 . 嵌入式相贯线焊接控制系统开发与实现[J]. 山东大学学报(工学版), 2008, 38(4): 37 -41 .
[3] 孔祥臻,刘延俊,王勇,赵秀华 . 气动比例阀的死区补偿与仿真[J]. 山东大学学报(工学版), 2006, 36(1): 99 -102 .
[4] 来翔 . 用胞映射方法讨论一类MKdV方程[J]. 山东大学学报(工学版), 2006, 36(1): 87 -92 .
[5] 余嘉元1 , 田金亭1 , 朱强忠2 . 计算智能在心理学中的应用[J]. 山东大学学报(工学版), 2009, 39(1): 1 -5 .
[6] 陈瑞,李红伟,田靖. 磁极数对径向磁轴承承载力的影响[J]. 山东大学学报(工学版), 2018, 48(2): 81 -85 .
[7] 王波,王宁生 . 机电装配体拆卸序列的自动生成及组合优化[J]. 山东大学学报(工学版), 2006, 36(2): 52 -57 .
[8] 季涛,高旭,孙同景,薛永端,徐丙垠 . 铁路10 kV自闭/贯通线路故障行波特征分析[J]. 山东大学学报(工学版), 2006, 36(2): 111 -116 .
[9] 秦通,孙丰荣*,王丽梅,王庆浩,李新彩. 基于极大圆盘引导的形状插值实现三维表面重建[J]. 山东大学学报(工学版), 2010, 40(3): 1 -5 .
[10] 张英,郎咏梅,赵玉晓,张鉴达,乔鹏,李善评 . 由EGSB厌氧颗粒污泥培养好氧颗粒污泥的工艺探讨[J]. 山东大学学报(工学版), 2006, 36(4): 56 -59 .
版权所有 © 2018 《山东大学学报(工学版)》编辑部　
地址: 济南市山大南路27号（250100）　 电话: 0531-88366735　 E-mail: xbgxb@sdu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发