基于局部注意力机制的中文短文本实体链接

doi:10.19678/j.issn.1000-3428.0059493

计算机工程 ›› 2021, Vol. 47 ›› Issue (11): 77-83,92. doi: 10.19678/j.issn.1000-3428.0059493

基于局部注意力机制的中文短文本实体链接

张晟旗¹, 王元龙¹, 李茹^1,2, 王笑月¹, 王晓晖¹, 闫智超¹

1. 山西大学计算机与信息技术学院, 太原 030006;
2. 山西大学计算机智能与中文信息处理教育部重点实验室, 太原 030006

收稿日期:2020-09-10 修回日期:2020-10-27 发布日期:2021-11-09
作者简介:张晟旗(1998-),男,硕士研究生,主研方向为中文信息处理;王元龙,副教授;李茹(通信作者),教授;王笑月、王晓晖、闫智超,硕士研究生。
基金资助:
国家自然科学基金“面向汉语篇章语义分析的框架推理技术研究”（61772324）；国家自然科学基金青年科学基金项目“基于事件的图文数据阅读理解关键技术研究”（61806117）。

Entity Linking Based on Local Attention Mechanism for Chinese Short Text

ZHANG Shengqi¹, WANG Yuanlong¹, LI Ru^1,2, WANG Xiaoyue¹, WANG Xiaohui¹, YAN Zhichao¹

1. School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China;
2. Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, Taiyuan 030006, China

Received:2020-09-10 Revised:2020-10-27 Published:2021-11-09

摘要/Abstract

摘要： 实体链接是加强语义理解和连接知识信息与文本的有效方法，但目前多数模型对上下文语境的精准理解受限于文本长度，面向短文本的实体链接任务存在实体边界识别错误和实体语义理解错误的问题。针对中文短文本的实体链接任务，构建基于局部注意力机制的实体链接模型。在实体消歧的过程中，通过对待消歧文本与实体的知识描述文本进行拼接，将短文本转换为长文本，同时引入局部注意力机制，缓解长距离依赖问题并强化局部的上下文信息。实验结果表明，相比于传统加入BIO标注方法的模型，该模型在CCKS2019和CCKS2020数据集上的F1值分别提升了4.41%和1.52%。

关键词: 实体链接, 上下文, 语义理解, 中文短文本, 局部注意力机制

Abstract: Entity linking is an effective method for strengthening semantic understanding and linking knowledge information to the text.However,the accuracy of most existing models in understanding the context is limited by the text length,so entity linking for short texts suffer from errors in entity boundary recognition and entity semantic understanding.To deal with the entity linking tasks for Chinese short texts,this paper proposes an entity linking model based on local attention mechanism.In the process of entity disambiguation,the short text is transformed into long text by concatenating the to-be-disambiguated text and the knowledge description text of the entity.At the same time,the local attention mechanism is introduced to alleviate the long-distance dependence and strengthen the local context information.Experimental results show that,compared with the traditional model with BIO labeling model,the proposed model increases the F1 value by 4.41% on the CCKS2019 data set and 1.52% on the CCKS2020 data set.

Key words: entity linking, context, semantic understanding, Chinese short text, local attention mechanism

中图分类号:

TP18

张晟旗, 王元龙, 李茹, 王笑月, 王晓晖, 闫智超. 基于局部注意力机制的中文短文本实体链接[J]. 计算机工程, 2021, 47(11): 77-83,92.

ZHANG Shengqi, WANG Yuanlong, LI Ru, WANG Xiaoyue, WANG Xiaohui, YAN Zhichao. Entity Linking Based on Local Attention Mechanism for Chinese Short Text[J]. Computer Engineering, 2021, 47(11): 77-83,92.

http://www.ecice06.com/CN/Y2021/V47/I11/77

图/表 7

20211113143542

20211113143545

20211113143549

20211113143552

20211113143554

20211113143557

20211113143600

参考文献

[1] 陆伟,武川.实体链接研究综述[J].情报学报,2015,34(1):105-112. LU W,WU C.Literature review on entity[J].Journal of the China Society for Scientific and Technical Information,2015,34(1):105-112.(in Chinese)
[2] 徐馨韬,柴小丽,谢彬,等.基于改进TextRank算法的中文文本摘要提取[J].计算机工程,2019,45(3):273-277. XU X T,CHAI X L,XIE B,et al.Extraction of Chinese text summarization based on improved TextRank algorithm[J]. Computer Engineering,2019,45(3):273-277.(in Chinese)
[3] 郭宇航,秦兵,刘挺,等.实体链指技术研究进展[J].智能计算机与应用,2014,4(5):9-13. GUO Y H,QIN B,LIU T,et al.Research progress of entity linking[J].Intelligent Computer and Applications,2014,4(5):9-13.(in Chinese)
[4] FINKEL J R,GRENAGER T,MANNING C.Incorporating non-local information into information extraction systems by gibbs sampling[C]//Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics.[S.l.]:ACL,2005:363-370.
[5] HE J Z,WANG H F.Chinese named entity recognition and word segmentation based on character[C]//Proceedings of the 6th SIGHAN Workshop on Chinese Language Processing.[S.l.]:ACL,2008:128-132.
[6] MAO X N,HE S K,BAO S C,et al.Chinese word segmentation and named entity recognition based on conditional random fields[C]//Proceedings of the 6th SIGHAN Workshop on Chinese Language Processing.[S.l.]:ACL,2007:90-93.
[7] LAMPLE G,BALLESTEROS M,SUBRAMANIAN S,et al.Neural architectures for named entity recognition[EB/OL].(2016-04-07)[2020-09-10].https://arxiv.org/pdf/1603.01360v3.pdf.
[8] TAN Z X,WANG M X,XIE J,et al.Deep semantic role labeling with self-attention[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence.[S.l.]:AAAI Press,2018:1-5.
[9] 李天然,刘明童,张玉洁,等.基于深度学习的实体链接方法研究[J].北京大学学报(自然科学版),2021,57(1):91-98. LI T R,LIU M T,ZHANG Y J,et al.A review of entity linking research based on deep learning[J].Acta Scientiarum Naturalium Universitatis Pekinensis,2021,57(1):91-98.
[10] SHEN W,WANG J Y,LUO P,et al.LINDEN:linking named entities with knowledge base via semantic knowledge[C]//Proceedings of Annual Conference on World Wide Web.Lyon,France:[s.n.]:2012:1-5.
[11] GANEA O E,HOFMANN T.Deep joint entity disambiguation with local neural attention[EB/OL].(2017-08-29)[2020-09-10].https://arxiv.org/pdf/1704.04920.pdf.
[12] KOLITSAS N,GANEA O E,HOFMANN T.End-to-end neural entity linking[EB/OL].(2018-08-29)[2020-09-10].https://arxiv.org/pdf/1808.07699v2.pdf.
[13] CAO P F,CHEN Y B,LIU K,et al.Adversarial transfer learning for Chinese named entity recognition with self-attention mechanism[C]//Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing.Brussels,Belgium:[s.n.],2018:1-5.
[14] SIL A,YATES A.Re-ranking for joint named-entity recognition and linking[C]//Proceedings of the 22nd ACM International Conference on Information and Knowledge Management.New York,USA:ACM Press,2013:2369-2374.
[15] 怀宝兴,宝腾飞,祝恒书,等.一种基于概率主题模型的命名实体链接方法[J].软件学报,2014,25(9):2076-2087. HUAI B X,BAO T F,ZHU H S,et al.Topic modeling approach to named entity linking[J].Journal of Software,2014,25(9):2076-2087.(in Chinese)
[16] LUO G,HUANG X J,LIN C Y,et al.Joint entity recognition and disambiguation[C]//Proceedings of 2016 Conference on Empirical Methods in Natural Language Processing.Austin,USA:[s.n.],2016:1-5.
[17] YANG X Y,GU X T,LIN S,et al.Learning dynamic context augmentation for global entity linking[EB/OL].(2019-09-04)[2020-09-10].https://arxiv.org/pdf/1909. 02117.pdf.
[18] XUE M G,CAI W M,SU J S,et al.Neural collective entity linking based on recurrent random walk network learning[EB/OL].(2019-06-20)[2020-09-10].https://arxiv.org/pdf/1906.09320.pdf.
[19] 吴晓崇,段跃兴,张月琴,等.基于CNN和深层语义匹配的中文实体链接模型[J].计算机工程与科学,2020,42(8):1514-1520. WU X C,DUAN Y X,ZHANG Y Q,et al.A Chinese entity linking model based on CNN and deep structured sematic model[J].Computer Engineering & Science,2020,42(8):1514-1520.(in Chinese)
[20] PETERS M,NEUMANN M,IYYER M,et al.Deep contextualized word representations[C]//Proceedings of 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.[S.l.]:ACL,2018:2227-2237.
[21] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.New York,USA:ACM Press,2017:5998-6008.
[22] DEVLIN J,CHANG M W,LEE K,et al.BERT:pre-training of deep bidirectional transformers for language understanding[EB/OL].(2018-10-11)[2020-09-10].https://arxiv.org/pdf/1810.04805v1.pdf.
[23] 詹飞,朱艳辉,梁文桐,等.基于BERT和TextRank关键词提取的实体链接方法[J].湖南工业大学学报,2020,34(4):63-70. ZHAN F,ZHU Y H,LIANG W T,et al.Entity linking via BERT and TextRank keyword extraction[J].Journal of Hunan University of Technology,2020,34(4):63-70.(in Chinese)
[24] LUONG M T,PHAM H,MANNING C D.Effective approaches to attention-based neural machine translation[EB/OL].(2015-09-20)[2020-09-10].https://arxiv.org/pdf/1508.04025.pdf.

选择文件类型/文献管理软件名称

选择包含的内容

基于局部注意力机制的中文短文本实体链接

Entity Linking Based on Local Attention Mechanism for Chinese Short Text

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	马坤, 安敬民, 李冠宇. 动态聚合实体和关系上下文的知识图谱补全[J]. 计算机工程, 2023, 49(8): 77-84, 95.
[2]	刘豪, 吴红兰, 房宇轩. 结合全局上下文信息的高效人体姿态估计[J]. 计算机工程, 2023, 49(7): 102-109.
[3]	顾轶寅, 王鸿奎, 殷海兵. 基于上下文自适应阈值剪枝的快速依赖量化算法[J]. 计算机工程, 2023, 49(7): 143-149.
[4]	李静雯, 赵奎. 基于改进PCFG算法的口令猜测方法[J]. 计算机工程, 2023, 49(5): 38-47.
[5]	苏鸣方, 胡立坤, 黄润辉. 基于上下文注意力的室外点云语义分割方法[J]. 计算机工程, 2023, 49(3): 248-256.
[6]	温静, 杨洁. 基于场景对象注意与深度图融合的深度估计[J]. 计算机工程, 2023, 49(2): 222-230.
[7]	黄奕秋, 胡晓, 杨佳信, 欧嘉敏. 基于背景抑制与上下文感知的人群计数网络[J]. 计算机工程, 2022, 48(9): 314-320.
[8]	张业星, 陈敏, 潘秋羽. 基于特征通道建模的目标检测方法[J]. 计算机工程, 2022, 48(7): 264-269,299.
[9]	王红霞, 何国昌, 李玉强, 陈德山. 基于改进U-Net的低质量文本图像二值化[J]. 计算机工程, 2022, 48(4): 231-239.
[10]	詹飞, 朱艳辉, 梁文桐, 张旭, 欧阳康, 孔令巍, 黄雅淋. 基于多任务学习的短文本实体链接方法[J]. 计算机工程, 2022, 48(3): 315-320.
[11]	张鹏举, 贾永辉, 陈文亮. 基于多特征实体消歧的中文知识图谱问答[J]. 计算机工程, 2022, 48(2): 47-54.
[12]	古平, 邱嘉涛, 罗长江, 张志鹏. 基于目标时空上下文融合的视频异常检测算法[J]. 计算机工程, 2022, 48(10): 169-175.
[13]	方义秋, 刘飞, 葛君伟. 基于Mogrifier LSTM的序列标注关系抽取方法[J]. 计算机工程, 2022, 48(10): 81-87,94.
[14]	张栋, 王铭涛, 陈文亮. 结合五笔字形与上下文相关字向量的命名实体识别[J]. 计算机工程, 2021, 47(3): 94-101.
[15]	霍占强, 王勇杰, 雒芬, 乔应旭. 基于超点图网络的三维点云室内场景分割模型[J]. 计算机工程, 2021, 47(12): 308-315.

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

基于局部注意力机制的中文短文本实体链接

Entity Linking Based on Local Attention Mechanism for Chinese Short Text

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献

相关文章 15

编辑推荐

Metrics

本文评价