[1]王坤,谢振平,陈梅婕.基于图约简的知识联想关系网络建模[J].智能系统学报,2019,14(04):679-688.[doi:10.11992/tis.201808009]
 WANG Kun,XIE Zhenping,CHEN Meijie.Modeling knowledge network on associative relations based on graph reduction[J].CAAI Transactions on Intelligent Systems,2019,14(04):679-688.[doi:10.11992/tis.201808009]
点击复制

基于图约简的知识联想关系网络建模(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第14卷
期数:
2019年04期
页码:
679-688
栏目:
出版日期:
2019-07-02

文章信息/Info

Title:
Modeling knowledge network on associative relations based on graph reduction
作者:
王坤 谢振平 陈梅婕
1. 江南大学 数字媒体学院, 江苏 无锡 214122;
2. 江苏省媒体设计与软件技术重点实验室, 江苏 无锡 214122
Author(s):
WANG Kun XIE Zhenping CHEN Meijie
1. School of Digital Media, Jiangnan University, Wuxi 214122, China;
2. Jiangsu Key Laboratory of Media Design and Software Technology, Wuxi 214122, China
关键词:
知识图谱联想记忆知识建模图约简知识网络知识联想记忆保留关系网络
Keywords:
knowledge graphassociative memoryknowledge modelinggraph reductionknowledge networkknowledge associationmemory reservationrelational network
分类号:
TP391
DOI:
10.11992/tis.201808009
摘要:
考虑到人类知识在大脑中以联想记忆形式存在,尝试从联想关系的视角深入探索知识体系的内在关系网络模型,旨在为知识图谱的建模提供一种可参考的新思路。对于给定的知识语料库,首先考虑以直接联想关系生成方式构建初始的知识关系网络,随后引入多种图约简方法优化知识联想关系网络的建模。研究中特别地提出了随机选择、局部联想最大记忆保留、全局联想最大记忆保留等3种知识联想关系约简重整策略,并通过实验手段对这3种策略进行建模分析。实验结果表明:3种方法呈现出了价值意义清晰的共同性能特征,而其中的全局联想最大记忆保留策略能最优地平衡知识联想关系网络的规模和联想记忆效率,可为相关应用提供有效的方法基础,也可为进一步探索类脑联想记忆的知识关系网络生成建模提供十分有益的启发。
Abstract:
Inspired by the fact that knowledge is stored in the form of associative memory in the human brain, we discuss the internal associative network model of knowledge system using associative relations, in order to provide a new train of thoughts referential to modeling knowledge graph. For a given knowledge corpus, an initial knowledge relation network was first constructed by producing direct associative relations, and then several graph reduction methods were introduced to optimize the modeling efficiency. Random selection and local and global strong memory reservation strategies were designed to reform the associative relations and their associative intensities, and experimental datasets were used to analyze these three modeling strategies. The experimental results show that the three different strategies exhibit interesting common characteristics. Moreover, global strong memory reservation strategy can optimize balance between the size of knowledge associative relation network and the associative memory efficiency. The results can provide a basis for related applications, as well as provide a meaningful understanding for exploring human-like knowledge associative memory modeling problems.

参考文献/References:

[1] SINGHAL A. Introducing the knowledge graph:things, not strings[R]. America:Official Blog of Google, 2012.
[2] SIMMONS R F. Technologies for machine translation[J]. Future generation computer systems, 1986, 2(2):83-94.
[3] SIMMONS R F. Natural language question-answering systems:1969[J]. Communications of the ACM, 1970, 13(1):15-30.
[4] YU Y H, SIMMONS R F. Truly parallel understanding of text[C]//Proceedings of the Eighth National Conference on Artificial Intelligence. Boston, Massachusetts, 1990:996-1001.
[5] ARENAS M, DÍAZ G, FOKOUE A, et al. A principled approach to bridging the gap between graph data and their schemas[J]. Proceedings of the VLDB endowment, 2014, 7(8):601-612.
[6] RAU L F. Extracting company names from text[C]//Proceedings. The Seventh IEEE Conference on Artificial Intelligence Application. Miami Beach, USA, 1991:29-32.
[7] LIU Xiaohua, ZHANG Shaodian, WEI Furu, et al. Recognizing named entities in tweets[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics:Human Language Technologies. Portland, Oregon, 2011:359-367.
[8] SOCHER R, CHEN Dandi, MANNING C D, et al. Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada, 2013:926-934.
[9] BOCCALETTI S, LATORA V, MORENO Y, et al. Complex networks:Structure and dynamics[J]. Physics reports, 2006, 424(4/5):175-308.
[10] 徐增林, 盛泳潘, 贺丽荣, 等. 知识图谱技术综述[J]. 电子科技大学学报, 2016, 45(4):589-606 XU Zenglin, SHENG Yongpan, HE Lirong, et al. Review on knowledge graph techniques[J]. Journal of university of electronic science and technology of China, 2016, 45(4):589-606
[11] 刘峤, 李杨, 段宏, 等. 知识图谱构建技术综述[J]. 计算机研究与发展, 2016, 53(3):582-600 LIU Qiao, LI Yang, DUAN Hong, et al. Knowledge graph construction techniques[J]. Journal of computer research and development, 2016, 53(3):582-600
[12] LI Yang, WANG Chi, HAN Fangqiu, et al. Mining evidences for named entity disambiguation[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Chicago, USA, 2013:1070-1078.
[13] HAN Xianpei, SUN Le, ZHAO Jun. Collective entity linking in web text:a graph-based method[C]//Proceedings of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval. Beijing, China, 2011:765-774.
[14] LEE T W, LEWICKI M S, GIROLAMI M, et al. Blind source separation of more sources than mixtures using overcomplete representations[J]. IEEE signal processing letters, 1999, 6(4):87-90.
[15] LU Shaoyuan, HSU K H, KUO Lijing. A semantic service match approach based on wordNet and SWRL rules[C]//Proceedings of the 2013 IEEE 10th International Conference on e-Business Engineering. Coventry, UK, 2013:419-422.
[16] 刘克彬, 李芳, 刘磊, 等. 基于核函数中文关系自动抽取系统的实现[J]. 计算机研究与发展, 2007, 44(8):1406-1411 LIU Kebin, LI Fang, LIU Lei, et al. Implementation of a kernel-based Chinese relation extraction system[J]. Journal of computer research and development, 2007, 44(8):1406-1411
[17] CARLSON A, BETTERIDGE J, WANG R C, et al. Coupled semi-supervised learning for information extraction[C]//Proceedings of the Third ACM International Conference on Web Search and Data Mining. New York, USA, 2010:101-110.
[18] ZHANG Yimin, ZHOU J F. A trainable method for extracting Chinese entity names and their relations[C]//Proceedings of the 2nd Workshop on Chinese Language Processing:Held in Conjunction with the 38th Annual Meeting of the Association for Computational Linguistics. Hong Kong, China, 2000:66-72.
[19] BANKO M, CAFARELLA M J, SODERLAND S, et al. Open information extraction from the web[C]//Proceedings of the 20th International Joint Conference on Artifical Intelligence. Hyderabad, India, 2007:2670-2676.
[20] 谢振平, 金晨, 刘渊. 基于建构主义学习理论的个性化知识推荐模型[J]. 计算机研究与发展, 2018, 55(1):125-138 XIE Zhenping, JIN Chen, LIU Yuan. Personalized knowledge recommendation model based on constructivist learning theory[J]. Journal of computer research and development, 2018, 55(1):125-138
[21] 刘知远, 孙茂松, 林衍凯, 等. 知识表示学习研究进展[J]. 计算机研究与发展, 2016, 53(2):247-261 LIU Zhiyuan, SUN Maosong, LIN Yankai. Knowledge representation learning:a review[J]. Journal of computer research and development, 2016, 53(2):247-261
[22] MICHEL A N, FARRELL J A. Associative memories via artificial neural networks[J]. IEEE control systems magazine, 1990, 10(3):6-17.
[23] BASSETT D S, MATTAR M G. A network neuroscience of human learning:potential to inform quantitative theories of brain and behavior[J]. Trends in cognitive sciences, 2017, 21(4):250-264.
[24] 刘冰瑶, 马静, 李晓峰. 一种"特征降维"文本复杂网络的话题表示模型[J]. 数据分析与知识发现, 2017, 1(11):53-61 LIU Bingyao, MA Jing, LI Xiaofeng. Topic representation model based on "feature dimensionality reduction"[J]. Data analysis and knowledge discovery, 2017, 1(11):53-61
[25] SUBBIAN K, AGGARWAL C, SRIVASTAVA J. Mining influencers using information flows in social streams[J]. ACM transactions on knowledge discovery from data, 2016, 10(3):26.
[26] ROSENBERG E. Maximal entropy coverings and the information dimension of a complex network[J]. Physics letters A, 2017, 381(6):574-580.
[27] 刘绍毓, 李弼程, 郭志刚, 等. 实体关系抽取研究综述[J]. 信息工程大学学报, 2016, 17(5):541-547 LIU Shaoyu, LI Bicheng, GUO Zhigang, et al. Review of entity relation extraction[J]. Journal of Information Engineering University, 2016, 17(5):541-547
[28] 美食百科[EB/OL].[2017-10-11]. https://www.meishi-baike.com. Meishi-baike[EB/OL].[201-10-11]. https://www.meishi-baike.com.
[29] 食品百科[EB/OL].[2017-10-12]. http://www.foodbk.com/. Foodbk[EB/OL].[2017-10-12]. http://www.foodbk.com/.
[30] 王灿辉. 搜狐新闻数据[EB/OL].[2017-11-03]. http://www.sogou.com/labs/resource/cs.php. WANG Canhui. Sohu news data[EB/OL].[2017-11-03]. http://www.sogou.com/labs/resource/cs.php.
[31] 搜狐体育[EB/OL].[2017-11-05]. http://sports.sohu.com/. Sohu Sports[EB/OL].[2017-11-05]. http://sports.sohu.com/.
[32] SHAO Ming, WU Xindong, FU Yun. Scalable nearest neighbor sparse graph approximation by exploiting graph structure[J]. IEEE transactions on big data, 2016, 2(4):365-380.

相似文献/References:

[1]张瑞成,胡绪磊.基于小世界网络的Hopfield联想记忆模型[J].智能系统学报,2014,9(02):214.[doi:10.3969/j.issn.1673-4785.201211050]
 ZHANG Ruicheng,HU Xulei.Research on the hopfield associative memory model based on the small-world network[J].CAAI Transactions on Intelligent Systems,2014,9(04):214.[doi:10.3969/j.issn.1673-4785.201211050]
[2]崔婉秋,杜军平,周南,等.基于用户意图理解的社交网络跨媒体搜索与挖掘[J].智能系统学报,2017,12(06):761.[doi:10.11992/tis.201706075]
 CUI Wanqiu,DU Junping,ZHOU Nan,et al.Social network cross-media searching and mining based on user intention[J].CAAI Transactions on Intelligent Systems,2017,12(04):761.[doi:10.11992/tis.201706075]
[3]常亮,张伟涛,古天龙,等.知识图谱的推荐系统综述[J].智能系统学报,2019,14(02):207.[doi:10.11992/tis.201805001]
 CHANG Liang,ZHANG Weitao,GU Tianlong,et al.Review of recommendation systems based on knowledge graph[J].CAAI Transactions on Intelligent Systems,2019,14(04):207.[doi:10.11992/tis.201805001]
[4]贾中浩,古天龙,宾辰忠,等.旅游知识图谱特征学习的景点推荐[J].智能系统学报,2019,14(03):430.[doi:10.11992/tis.201810032]
 JIA Zhonghao,GU Tianlong,BIN Chenzhong,et al.Tourism knowledge-graph feature learning for attraction recommendations[J].CAAI Transactions on Intelligent Systems,2019,14(04):430.[doi:10.11992/tis.201810032]

备注/Memo

备注/Memo:
收稿日期:2018-06-12。
基金项目:国家自然科学基金项目(61872166);江苏省科技计划项目(BE2018056).
作者简介:王坤,男,1991年生,硕士研究生,主要研究方向为机器学习、知识网络;谢振平,男,1979年生,副教授,博士,CCF会员,主要研究方向为知识网络、演化学习、认知物理学。承担完成国家、省部级科研项目10项,负责承担完成产学研应用项目13项,正在主持国家自然科学基金面上项目、江苏省重点研发计划项目子课题等研究;陈梅婕,女,1995年生,硕士研究生,主要研究方向为机器学习、自然语言处理。
通讯作者:谢振平.E-mail:xiezhenping@hotmail.com
更新日期/Last Update: 2019-08-25