甲骨文知识图谱构建中的实体关系发现研究

摘要/Abstract

摘要：

为解决甲骨文信息处理研究中对专家的依赖性高而专家知识共享率却很低这一突出矛盾，提出构建知识图谱的方案，其核心问题是如何发现实体和实体间的关联关系。基于甲骨文的古籍特征，先通过知识图谱MKD的共词分析发现实体及其关系，再利用甲骨文本体和规则推理发现隐含的语义关系，最后将其与MKD共词关系进行融合。实验结果表明，该方法可以有效解决甲骨文知识图谱中实体关系发现问题。

关键词: 甲骨文, 知识图谱, 本体, 语义相似度, 甲骨文知网

Abstract:

During the research process of Oracle Bone Inscriptions (OBI ) information processing, there is a prominent contradiction between high dependence on experts and low sharing of their OBI knowledge.In order to solve this problem, we propose an OBI knowledge mapping scheme, the crucial issue of which is how to find the ontology relations.Firstly,based on the OBI features,the coword analysis of Mapping Knowledge Domains (MKD) is done to find the ontology relations. Secondly, OBI ontology and reasoning are used to find the implicit semantic relations. Finally, the coword relations and ontology relations are fused to describe the OBI knowledge mapping relations.Experimental results show that the method can effectively solve the problem of entity relation discovery in OBI knowledge mapping construction.

Key words: Oracle Bone Inscriptions;knowledge mapping;ontology;semantic similarity;OBIHownet

熊晶1，钟珞2，王爱民1,2. 甲骨文知识图谱构建中的实体关系发现研究[J]. J4, 2015, 37(11): 2188-2194.

XIONG Jing1，ZHONG Luo2，WANG Aimin1, 2. Research on entity relation discovery for Oracle Bone
Inscriptions knowledge mapping construction [J]. J4, 2015, 37(11): 2188-2194.

参考文献

［1］Xiong Jing, Gao Feng, Wu Qinxia. Research on semantic mining for largescale oracle bone inscriptions foundation data ［J］. New Technology of Library and Information Service, 2015, 31(2):714. (in Chinese)
［2］Jiang Minghu. Natural language processing［M］. Beijing:Higher Education Press, 2006. (in Chinese)
［3］Xiong Jing, Zhong Luo, Wang Aimin. Example and ontology based machine translation for oracle bone inscriptions ［J］. Journal of Huazhong University of Science and Technology (Nature Science Edition), 2013, 41(S2):222226. (in Chinese)
［4］Qin Changjiang, Hou Hanqing. Mapping knowledge domaina new field of information management and knowledge management ［J］. Journal of Academic Libraries, 2009, 27(1):3037. (in Chinese)
［5］Hu Zewen, Sun Jianjun, Wu Yishan. Research review on application of knowledge mapping in China ［J］. Library and Information Service, 2013, 57(3):131137. (in Chinese)
［6］Liu Zeyuan,Chen Yue,Hou Haiyan,et al. Mapping knowledge domains methods and application ［M］. Beijing:People’s Publishing House, 2008. (in Chinese)
［7］Chen C, Ibekwe Sanjuan F, Hou J. The structure and dynamics of cocitation clusters:A multipleperspective cocitation analysis［J］. Journal of the American Society for Information Science and Technology, 2010, 61(7):13861409.
［8］Chen C.CiteSpace II:Detecting and visualizing emerging trends and transient patterns in scientific literature ［J］. Journal of the American Society for information Science and Technology, 2006, 57(3):359377.
［9］Tang Jianmin, Yu Fengmin. Review and evaluation of knowledge mapping research in China:20042010 ［J］. Information and Documentation Services, 2012(1):1621. (in Chinese)
［10］Chen Yue,Liu Zeyuan.The rise of mapping knowledge domain ［J］. Studies in Science of Science, 2005, 23(2):149154. (in Chinese)
［11］Bizer C, Heath T, BernersLee T. Linked datathe story so far ［J］. International Journal on Sematic Web and Information Systems, 2009,5(3):122.
［12］Gattani A. Entity extraction, linking, classification, and tagging for social media:A wikipediabased approach［J］. Proceeding of the VLDB Endowment, 2013, 6(11):11261137.
［13］Deshpande O,Lamba D S,Tourn M,et al.Building, maintaining, and using knowledge bases:A report from the trenches［C］∥Proc of the 2013 ACM SIGMOD International Conference on Management of Data, 2013:12091220.
［14］Dong X, Gabrilovich E, Heitz G, et al. Knowledge vault:A webscale approach to probabilistic knowledge fusion［C］∥Proc of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014:601610.
［15］Wu C, Wang H, Qu J, et al. ZhishiLink:entity linking on zhishi.me ［C］∥Proc of the 7th China Sematic Web Symposium,2013:161174.
［16］Wang Z, Li J, Wang Z, et al. XLore:A largescale EnglishChinese bilingual knowledge graph［C］∥Proc of International Semantic Web Conference (Posters & Demos), 2013:121124.
［17］Xu M, Wang Z, Bie R, et al. Discovering missing semantic relations between entities in Wikipedia［C］∥Proc of the Semantic WebISWC 2013,2013:673686.
［18］Wang Z, Li J, Tang J. Boosting crosslingual knowledge linking via concept annotation［C］∥Proc of the 23rd International Joint Conference on Artificial Intelligence, 2013:27332739.
［19］Wang Jianfang.Analysis method of mapping knowledge domains based on ontology ［EB/OL］.［20140115］. http://ir.las.ac.cn/handle/12502/3837. (in Chinese)
［20］Xiao Zhixiong, Gu Jing. Coword analysisbased study on research hotspots of synergetics in China ［J］. Information Research, 2015(5):69. (in Chinese)
［21］Borst W N.Construction of engineering ontologies for knowledge sharing and reuse ［D］. Ensched:Universiteit Twente, 1997.
［22］Liu Hongzhe, Xu De. Ontology based semantic similarity and relatedness measures review ［J］. Computer Science, 2012, 39(2):813. (in Chinese)
［23］Dong Z, Dong Q, Hao C. Hownet and its computation of meaning［C］∥Proc of the 23rd International Conference on Computational Linguistics:Demonstrations, 2010:5356.
［24］Xiong Jing, Wang Aimin, Xu Jianliang. Information retrieval optimization strategy based on domain ontology［J］. Computer Engineering and Design, 2011, 32(8):26952699. (in Chinese)
附中文参考文献：
［1］熊晶, 高峰, 吴琴霞. 甲骨文大规模基础数据的语义挖掘研究［J］. 现代图书情报技术, 2015, 31(2):714.
［2］江铭虎. 自然语言处理［M］. 北京:高等教育出版社, 2006.
［3］熊晶, 钟珞, 王爱民. 基于实例和本体的甲骨文机器翻译方法研究［J］. 华中科技大学学报(自然科学版), 2013, 41(S2):222226.
［4］秦长江, 侯汉清. 知识图谱——信息管理与知识管理的新领域［J］. 大学图书馆学报, 2009, 27(1):3037.
［5］胡泽文, 孙建军, 武夷山. 国内知识图谱应用研究综述［J］. 图书情报工作, 2013, 57(3):131137.
［6］刘则渊,陈悦,侯海燕,等.科学知识图谱:方法与应用［M］. 北京:人民出版社, 2008.
［9］汤建民, 余丰民. 国内知识图谱研究综述与评估:20042010 年［J］. 情报资料工作, 2012(1):1621.
［10］陈悦, 刘则渊. 悄然兴起的科学知识图谱［J］. 科学学研究, 2005, 23(2):149154.
［19］王建芳. 基于本体的科学知识图谱分析方法研究［EB/OL］.［20140115］. http://ir.las.ac.cn/handle/12502/3837.
［20］肖志雄, 谷静. 基于共词分析法的国内协同学研究热点分析［J］. 情报探索, 2015(5):69.
［22］刘宏哲,须德. 基于本体的语义相似度和相关度计算研究综述［J］. 计算机科学, 2012, 39(2):813.
［24］熊晶, 王爱民, 徐建良. 基于领域本体的信息检索优化策略［J］.计算机工程与设计, 2011, 32(8):26952699.

[1]	张若一, 金柳, 马慧芳, 王亦可, 李清风. 融合相似用户影响效应的知识图谱推荐模型[J]. 计算机工程与科学, 2023, 45(03): 520-527.
[2]	马赫, 王海荣, 周北京, 孙崇, 徐玺. 基于表示学习的实体对齐方法综述[J]. 计算机工程与科学, 2023, 45(03): 554-564.
[3]	林庆, 滕飞, 田波, 赵越, 祝锦烨, 冯力. 基于可搜索加密的密态知识图谱存储和检索方案[J]. 计算机工程与科学, 2023, 45(01): 66-76.
[4]	邹程辉, 李卫疆, . 融合知识图谱和评论文本的个性化推荐模型[J]. 计算机工程与科学, 2023, 45(01): 181-190.
[5]	裴凇莹, 陈振国. 基于文献计量的国内区块链技术研究及应用态势分析[J]. 计算机工程与科学, 2021, 43(11): 1966-1978.
[6]	顾军华, 佘士耀, 樊帅, 张素琪. 基于用户长短期兴趣与知识图卷积网络的推荐[J]. 计算机工程与科学, 2021, 43(03): 511-517.
[7]	赵俊生, 王鑫宇, 尹玉洁, 张林. 基于蒙古语新闻领域本体的分布式检索方法[J]. 计算机工程与科学, 2021, 43(03): 560-570.
[8]	魏墨济, 赵燕清, 朱世伟, 李晨. 基于社会立场建模的网络犯罪预警研究[J]. 计算机工程与科学, 2021, 43(01): 151-160.
[9]	沈冬东, 汪海涛, 姜瑛, 陈星. 基于知识图谱嵌入与多神经网络的序列推荐算法[J]. 计算机工程与科学, 2020, 42(09): 1661-1669.
[10]	吴晓崇, 段跃兴, 张月琴, 闫雄. 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(08): 1514-1520.
[11]	郭竞知, 刘玮, 徐龙龙, 陈灯 . Agent能力承诺协作的自适应图规划协议生成算法[J]. 计算机工程与科学, 2020, 42(07): 1208-1214.
[12]	袁泉1,2,3,成振华1,2,江洋1,2. 基于知识图谱和协同过滤的电影推荐算法研究[J]. 计算机工程与科学, 2020, 42(04): 714-721.
[13]	陈鑫1，王斌1，曾范清2. 商品搭配大数据推荐方法研究综述[J]. 计算机工程与科学, 2020, 42(01): 36-45.
[14]	王亚强1,2，臧根林1,2，吴庆蓉1,2，占春丽1,2，谢新扬1,2. 一种领域知识图谱的本体根类型设计[J]. 计算机工程与科学, 2019, 41(10): 1861-1867.
[15]	赵维平1，孙宁2，杨晓春3，郑国真4. 基于知识图谱的东方音乐可视化教育研究与应用[J]. 计算机工程与科学, 2018, 40(增刊S1): 56-62.