Please wait a minute...
浙江大学学报（理学版）
浙江大学学报（理学版）  2020, Vol. 47 Issue (2): 142-150    DOI: 10.3785/j.issn.1008-9497.2020.02.002
文字与计算     
网络驱动的未识甲骨字特性及场景语义预测
焦清局1,2,3, 刘永革1,2,3, 仇利萍4,5, 金园园1, 熊晶1,2,3, 刘国英1,2,3, 高峰1,2,3
1.安阳师范学院 计算机与信息工程学院，河南 安阳 455000
2.甲骨文信息处理教育部重点实验室，河南 安阳 455000
3.河南省甲骨文信息处理重点实验室，河南 安阳 455000
4.安阳师范学院 历史与文博学院，河南 安阳 455000
5.中国社会科学院先秦史研究所，北京 100732
Network-driven prediction of unknown oracle character’s features and scene semantics
JIAO Qingju1,2,3, LIU Yongge1,2,3, QIU Liping4,5, JIN Yuanyuan1, XIONG Jing1,2,3, LIU Guoying1,2,3, GAO Feng1,2,3
1.School of Computer & Information Engineering, Anyang Normal University, Anyang 455000, Henan Province, China
2.Key Laboratory of Oracle Bone Inscriptions Information Processing, Ministry of Education of China, Anyang 455000, Henan Province, China
3.Key Laboratory of Oracle Information Processing in Henan Province, Anyang 455000, Henan Province, China
4.Faculty of History and Archaeology, Anyang Normal University, Anyang 455000, Henan Province, China
5.Institute of Pre-Qin History, Chinese Academy of Social Science, Beijing 100732, China
 全文: PDF(2962 KB)   HTML  
摘要： 甲骨学的研究具有重要的文化价值和传承意义，可以极大提高国家的文化自信。未识甲骨字的语义预测是甲骨学研究中最主要的问题，也是传统甲骨学研究中最棘手的问题。现有的计算机技术辅助研究方法无法预测未识甲骨字的语义。利用复杂网络对甲骨文进行了抽象和理解，并对未识甲骨字的场景语义进行预测。首先，以甲骨拓片为基础数据，通过建模构建甲骨字网络；其次，在甲骨字网络之上，分析未识甲骨字的重要性、信息丰富度、闭合性等特性，为预测未识甲骨字的场景语义提供理论依据；最后，根据网络特性和甲骨拓片的上下文语境预测未识甲骨字的场景语义。构建的未识甲骨字特性体系以及预测未识甲骨字的场景语义思路为破译其他未识甲骨字的语义奠定了基础，有助于推动甲骨文考释的进程。
关键词： 甲骨文;  场景语义;  复杂网络;  预测    
Abstract: The research of oracle bone inscriptions is of important cultural values and inheritance significance, which can greatly enhance the country's cultural self-confidence. The semantic prediction of unknown oracle characters is recognized as the most important and difficult problem in studying oracle bone inscriptions, In this paper, we use complex networks to abstract and understand oracle bone inscriptions and predict the semantics of unknown oracle characters. First , we employ the oracle bone rubbings to build the oracle character network. Then, we analyze the importance, information richness and closure of unknown oracle characters based on oracle character network, these features can provide vital theories in predicting semantics of unknown oracle characters. Finally,the scene semantics of the unknown oracle characters are predicted according to the network characteristics and context of oracle bone rubbings. The features of unknown oracle characters and the process of prediction scene semantics of the unknown oracle characters provide researchers with potential to explore new approach, and promote the process of oracle bones interpretation.
Key words: oracle bone inscriptions    scene semantics    complex network    prediction
收稿日期: 2019-12-17 出版日期: 2020-03-25
CLC:  TP391  
基金资助: 国家自然科学基金资助项目(61806007，U1804153)；教育部、国家语委甲骨文研究与应用专项(YWZ-J023，YWZ-J010，YB135-50)；河南省科技攻关项目(182102310039)；国家社会科学基金重大委托项目(16@ZH017A3).
作者简介: 焦清局(1983—)，ORCID: 0000-0002-5608-371X，男，博士，讲师，主要从事模式识别，复杂网络，甲骨文信息处理研究，E-mail：qjjiao@aynu.edu.cn.
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
焦清局
刘永革
仇利萍
金园园
熊晶
刘国英
高峰

引用本文:

焦清局, 刘永革, 仇利萍, 金园园, 熊晶, 刘国英, 高峰. 网络驱动的未识甲骨字特性及场景语义预测[J]. 浙江大学学报（理学版）, 2020, 47(2): 142-150.

JIAO Qingju, LIU Yongge, QIU Liping, JIN Yuanyuan, XIONG Jing, LIU Guoying, GAO Feng. Network-driven prediction of unknown oracle character’s features and scene semantics. Journal of Zhejiang University (Science Edition), 2020, 47(2): 142-150.

链接本文:

https://www.zjujournals.com/sci/CN/10.3785/j.issn.1008-9497.2020.02.002    或    https://www.zjujournals.com/sci/CN/Y2020/V47/I2/142

1 刘永革，栗青生. 可视化甲骨文输入法的设计与实现[J]. 计算机工程与应用，2004, 17：139-140. LIUY G, LIQ S. Design and implementation of visual input method of oracular inscriptions on tortoise shells and bones[J]. Computer Engineering and Applications, 2004, 17: 139-140.
2 肖明，赵慧，甘仲惟. 甲骨文象形码编码的模糊数学模型研究[J]. 计算机工程与设计，2004, 25(3)：358-361. DOI:10.16208/j.issn1000-7024.2004.03.013 XIAOM, ZHAOH, GANZ W. Study for fuzzy mathematics model of Jiaguwen symbol code[J]. Computer Engineering and design, 2004(3), 25(3): 358-361.DOI:10.16208/j.issn1000-7024.2004.03.013
3 顾绍通，马小虎，杨亦鸣. 基于字形拓扑结构的甲骨文输入编码研究[J]. 中文信息学报，2008, 22(4)：123-128. GUS T, MAX H, YANGY M. Topological frame based input method coding of Jiaguwen[J]. Journal of Chinese Information Processing, 2008, 22(4): 123-128.
4 聂艳召，刘永革. 甲骨文自由笔画输入法[J]. 中文信息学报，2010, 24(6)：103-107.DOI:10.3969/j.issn.1003-0077.2010.06.017 NIEY Z, LIUY G. Free stroke input method for carapace-bone-script[J]. Journal of Chinese Information Processing, 2010, 24(6): 103-107.DOI:10.3969/j.issn.1003-0077.2010.06.017
5 栗青生，杨玉星，王爱民. 甲骨文识别的图同构方法[J]. 计算机工程与应用，2011, 47(8)：112-114. LIQ S, YANGY X, WANGA M. Recognition of inscriptions on bones or tortoise shells based on graph isomorphism[J]. Computer Engineering and Applications, 2011, 47(8): 112-114.
6 高峰，吴琴霞，刘永革，等. 基于语义构件的甲骨文模糊字形的识别方法[J]. 科学技术与工程，2014, 14(30)：67-71. GAOF, WUQ X, LIUY G, et al. Recognition of fuzzy inscription character based on component for bones or tortoise shells[J]. Science Technology and Engineering, 2014, 14(30): 67-71.
7 顾绍通. 基于拓扑配准的甲骨文字形识别方法[J]. 计算机与数字工程，2016, 44(10)：2001-2006. GUS T. Identification of oracle-bone script fonts based on topological registration[J]. Computer and Digital Engineering, 2016, 44(10): 2001-2006.
8 GUOF, WANGC, ROMAN-RANGElE, et al. Building hierarchical representations for oracle character and sketch recognition [J]. IEEE Transactions on Image Processing, 2016, 25(1): 104-118. DOI:10.1109/tip.2015.2500019
9 袁冬，熊晶，刘永革. 面向甲骨文的实例机器翻译技术研究[J]. 现代图书情报技术，2012（5）：48-54. YUAND, XIONGJ, LIUY G. Research on example-Based machine translation for oracle bone inscriptions[J]. New Technology of Library and Information Service, 2012（5）: 48-54.
10 高峰，熊晶，刘永革. 基于知网的甲骨卜辞释义问题的可拓性研究[J]. 现代图书情报技术，2015（7）：58-64. GAOF, XIONGJ, LIUY G. Research on the extenics of oracle bone inscriptions interpretation based on howNet[J]. New Technology of Library and Information Service, 2015（7）: 58-64.
11 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（2）：7-14. XIONGJ, GAOF, WUQ X. Research on semantic mining for large-scale oracle bone inscriptions foundation data[J]. New Technology of Library and Information Service, 2015, 2: 7-14.
12 DRESSA, GRUNEWALDS, ZENGZ. A cognitive network for oracle bone characters related to animals[J]. International Journal of Modern Physics B, 2016, 30(4): 1630001.
13 焦清局，高峰，金园园，等. 面向拓片信息的甲骨字网络构建与分析[J]. 中文信息学报，2018, 32(7)：137-142. JIAOQ J, GAOF, JINY Y, et al. Construction and analysis of rubbing-oriented oracle character network[J]. Journal of Chinese Information Processing, 2018, 32(7): 137-142.
14 LIUH. Language as a human-driven complex adaptive system: comment on “Rethinking foundations of language from a multidisciplinary perspective” by T. Gong et al[J]. Physics of Life Reviews, 2018, 26-27: 149-151.
15 赵怿怡，刘海涛. 语言网络研究的数学模型[J]. 中文信息学报，2015, 29(6)：46-53. ZHAOY Y, LIUH T. Mathematical modeling in language networks research[J]. Journal of Chinese Information Processing, 2015, 29(6): 46-53.
16 CANCHOR F I, SOLER V. The small world of human language[J]. Proceedings of the Royal Society of London （Ser B）：Biological Science, 2001, 268: 2261-2265.
17 STEYVERSM, TENENBAUMJ B. The large-scale structure of semantic networks: statistical analysis and a model of semantic growth[J]. Cognitive Science, 2005, 29: 41-78.DOI:10.1207/s15516709cog2901_3
18 韦洛霞，李勇，康世勇，等. 汉语词组网的组织结构与无标度特性[J]. 科学通报，2005, 50(15)：1575-1579. WEIL X, LIY, KANGS Y, et al. Structural organization and scale-free properties in Chinese phrase networks[J]. Chinese Science Bulletin, 2005, 50(15): 1575-1579.
19 ARBESMANS, STROGATZS H, VITEVITCHM S. Comparative analysis of networks of phonologically similar words in English and Spanish[J]. Entropy, 2010, 12: 327-337.DOI:10.3390/e12030327
20 SIEWC S Q. Community structure in the phonological network[J]. Frontiers in Psychology, 2013（4）: 553. DOI:10.3389/fpsyg.2013.00553
21 DAUTRICHEI, MAHOWALDK, GIBSONE, et al. Words cluster phonetically beyond phonotactic regularities[J]. Cognition, 2017, 163: 128-145.DOI:10.1016/j.cognition.2017.02.001
22 LIANGW, WANGK. Relationships among the statistical parameters in evolving modern Chinese linguistic co-occurrence networks[J]. Physica A: Statistical Mechanics and Its Applications, 2019, 524: 532-539. DOI:10.1016/j.physa.2019.04.100
23 ARRUDAH F, MARINHOV Q, COSTAL F, et al. Paragraph-based representation of texts: A complex networks approach[J]. Information Processing and Management, 2019, 56: 479-494. DOI:10.1016/j.ipm.2018.12.008
24 SIEWC S Q, WULFFD U, BECKAGEN M, et al. Cognitive network science: A review of research on cognition through the lens of network representations, processes, and dynamics[J]. Complexity, 2019, 2108423. DOI:10.31234/osf.io/eu9tr
25 SIZEMOREA E, KARUZAE A, GIUSTIC, et al. Knowledge gaps in the early growth of semantic feature networks[J]. Nature Human Behaviour, 2018（2）: 682-692. DOI:10.1038/s41562-018-0422-4
26 HAGOORTP. The neurobiology of language beyond single-word processing[J]. Science, 2019, 366: 55-58.DOI:10.1126/science.aax0289
27 FREEMANL C. A set of measures of centrality based on betweenness[J]. Sociometry, 1977, 40(1): 35-41. DOI:10.2307/3033543
28 陈梦家. 殷墟卜辞综述[M]. 北京：中华书局，2016. CHENM J. The Review of Oracle Inscription of the Shang Dynasty[M]. Beijing：Zhonghua Book Company, 2016.
29 于省吴. 甲骨文字诂林[M]. 北京：中华书局，1999. YUX W. Oracle Bone Inscription [M]. Beijing：Zhonghua Book Company, 1999.
30 LECUNY, BENGIOY, HINTONG. Deep learning[J]. Nature, 2015, 521(2): 436-444.
31 SUTSKEVERI, MARTENSJ, HINTONG. Generating text with recurrent neural networks[C]//Proceeding ICML'11 Proceedings of the 28th International Conference on International Conference on Machine Learning. Bellevue: IMLS，2011： 1017-1024.
32 CHOWDHURYS A, ZAMPARELLIR. RNN simulations of grammaticality judgments on long-distance dependencies[C]//Proceedings of the 27th International Conference on Computational Linguistics. Santa Fe: ICCL，2018：133-144.
33 POPEP E, KOLOURIS, ROSTAMIM, et al. Explainability methods for graph convolutional neural networks[C]// The IEEE Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE，2019：10772-10781. DOI:10.1109/cvpr.2019.01103
34 HOCHREITERS, SCHMIDHUBERJ. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
35 MAY, PENGH, CAMBRIAE. Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM[C]//The Thirty-Second AAAI Conference on Artificial Intelligence.New Orleans : AAAI， 2018： 5876-5883.
36 徐冰冰，岑科廷，黄俊杰，等. 图卷积神经网络综述[J]. 计算机学报，2019, 42(122): 1-31. XUB B, CENK T, HUANGJ J, et al. A survey on graph convolutional neural network[J]. Chinese Journal of Computers, 2019, 42(122): 1-31.
[1] 康俊锋,符悦,方雷,李咪咪,谢玉静,周朝阳. 基于最小二乘法赋权的ARIMA-LSTM模型预测入境旅游人数——以上海市为例[J]. 浙江大学学报（理学版）, 2023, 50(4): 508-520.
[2] 郑素佩, 靳放, 封建湖, 林云云. 双曲型方程激波捕捉的物理信息神经网络（PINN）算法[J]. 浙江大学学报（理学版）, 2023, 50(1): 56-62.
[3] 常晓洁,张华. 一种基于V-TGRU模型的资源调度算法[J]. 浙江大学学报（理学版）, 2022, 49(4): 467-473.
[4] 王昱文, 杜震洪, 戴震, 刘仁义, 张丰. 基于复合神经网络的多元水质指标预测模型[J]. 浙江大学学报（理学版）, 2022, 49(3): 354-362.
[5] 徐敏, 王科, 戴浩然, 罗晓博, 余炜伦, 陶煜波, 林海. 基于电子病历的乳腺癌群组与治疗方案可视分析[J]. 浙江大学学报（理学版）, 2021, 48(4): 391-401.
[6] 钱立辉, 王斌, 郑云飞, 章佳杰, 李马丁, 于冰. 基于图像深度预测的景深视频分类算法[J]. 浙江大学学报（理学版）, 2021, 48(3): 282-288.
[7] 傅颖颖, 张丰, 杜震洪, 刘仁义. 融合图卷积神经网络和注意力机制的PM2.5小时浓度多步预测[J]. 浙江大学学报（理学版）, 2021, 48(1): 74-83.
[8] 任欢, 刘婷, 康俊锋, 潘宁, 李敏靓, 艾顺毅. 一种基于百度指数的城市日游客规模预测方法[J]. 浙江大学学报（理学版）, 2020, 47(6): 753-761.
[9] 曾亮. 基于振荡序列的灰色GM(1,1|sin)幂模型及其应用[J]. 浙江大学学报（理学版）, 2019, 46(6): 697-704.
[10] 黄婕, 张丰, 杜震洪, 刘仁义, 曹晓裴. 基于RNN-CNN集成深度学习模型的PM2.5小时浓度预测[J]. 浙江大学学报（理学版）, 2019, 46(3): 370-379.
[11] 赵亚莉, 刘浩滢, 厉子龙, 邹思远, 孙浩伟, 励音骐, 杨树锋, 陈汉林, 成军. 多元统计分析在塔里木瓦吉里塔格钒钛磁铁矿床多元素相关性及成矿预测研究中的应用[J]. 浙江大学学报（理学版）, 2016, 43(6): 716-725.
[12] 秦中伏, 雷小龙, 翟东, 金灵志. 基于SVM和LS-SVM的住宅工程造价预测研究[J]. 浙江大学学报（理学版）, 2016, 43(3): 357-363.