1.湖南师范大学 基础教育大数据研究与应用重点实验室,湖南 长沙 410006
2.厦门大学 教育研究院,福建 厦门 361005
3.湖南师范大学 工程与设计学院,湖南 长沙 410006
4.武汉大学 计算机学院, 湖北 武汉 430072
周炫余,男,讲师,现从事中文自然语言处理、教育人工智能等方面的研究。E-mail:zhouxuanyu@whu.edu.cn
E-mail: xlu_hnu@163.com
纸质出版日期:2021-04-24,
收稿日期:2020-11-08,
扫 描 看 全 文
引用本文
周炫余,唐祯,唐丽蓉, 等.基于多源异构数据融合的初中数学知识图谱构建[J].武汉大学学报(理学版),2021,67(2):118-126.
ZHOU Xuanyu,TANG Zhen,TANG Lirong,et al.Construction of Junior High School Mathematics Knowledge Graph Based on Multi-Source Heterogeneous Data Fusion [J].J Wuhan Univ (Nat Sci Ed),2021,67(2):118-126.
周炫余,唐祯,唐丽蓉, 等.基于多源异构数据融合的初中数学知识图谱构建[J].武汉大学学报(理学版),2021,67(2):118-126. DOI:10.14188/j.1671-8836.2020.0273
ZHOU Xuanyu,TANG Zhen,TANG Lirong,et al.Construction of Junior High School Mathematics Knowledge Graph Based on Multi-Source Heterogeneous Data Fusion [J].J Wuhan Univ (Nat Sci Ed),2021,67(2):118-126. DOI:10.14188/j.1671-8836.2020.0273(Ch).
知识图谱可以为智能问答和自动推荐等系统提供良好的数据支持。针对国内现有学科知识图谱构建数据来源单一等问题,提出一种多源异构数据融合的方法构建初中数学知识图谱。基于领域知识和学习者需求构建初中数学本体,确定概念、方法、公式、定理四种类型的实体;从教材等权威数据源和百度百科、互动百科等网络数据源中获取非结构化与半结构化数据,基于BERT(bidirectional encoder representations from transforms)模型抽取出教材等非结构化数据的关系和实体;利用基于层次过滤思想的知识融合模型进行多源异构数据的融合。实现了基于初中数学知识图谱的智能问答和自动推荐系统,为学习者提供及时且智能的学习支持服务,为破解初中数学在线教学个性化不足提供一条思路。
Knowledge graph can provide good data supporting for the intelligent question-answering system and automatic recommendation system. This paper proposes a method of multi-source heterogeneous data fusion to construct junior high school mathematics knowledge graph to solve the problem of a single data source of the existing subject knowledge graph in China. First, the junior high school mathematics ontology was constructed to determine four types of entities: concept, method, formula and theorem based on the domain knowledge and learners' needs. Then, unstructured and semi-structured data were obtained from authoritative data sources such as textbooks and network data sources such as Baidu Wikipedia, HDWiki, and the relationships and entities of unstructured data were extracted from the BERT(bidirectional encoder representations from transforms) model. Then the knowledge fusion model based on multi-pass sieve was used to fuse heterogeneous data from multiple sources. Finally, the intelligent question-answering and automatic recommendation system based on the knowledge graph of junior high school mathematics is realized. This study can provide learners with timely and intelligent learning support services, so as to provide an idea for solving the insufficiency of personalization in the online teaching of junior high school mathematics.
知识图谱多源异构数据融合层次过滤模型初中数学
knowledge graphmulti-source heterogeneous data fusionmulti-pass sieve modeljunior high school mathematics
喻平, 董林伟. 初中数学实验的本质解析[J]. 课程·教材·教法, 2016, 36(8): 89-95. DOI: 10.19877/j.cnki.kcjcjf.2016.08.014http://dx.doi.org/10.19877/j.cnki.kcjcjf.2016.08.014.
YU P, DONG L W. Analysis of nature of mathematics experiment in junior middle school [J]. Curriculum,Teaching Material and Method, 2016, 36(8): 89-95. DOI: 10.19877/j.cnki.kcjcjf.2016.08.014(Chhttp://dx.doi.org/10.19877/j.cnki.kcjcjf.2016.08.014(Ch).
李艳燕, 张香玲, 李新, 等. 面向智慧教育的学科知识图谱构建与创新应用[J]. 电化教育研究, 2019, 40(8): 60-69. DOI:10.13811/j.cnki.eer.2019.08.008http://dx.doi.org/10.13811/j.cnki.eer.2019.08.008.
LI Y Y, ZHANG X L, LI X, et al. Construction and innovative application of discipline knowledge graph oriented to smart education [J]. E-Education Research, 2019, 40(8): 60-69. DOI:10.13811/j.cnki.eer.2019.08.008(Chhttp://dx.doi.org/10.13811/j.cnki.eer.2019.08.008(Ch).
朱游娟. 初中数学问题的全知识图谱设计与实现[D].成都:电子科技大学,2016. DOI:10.7666/d.D00990642http://dx.doi.org/10.7666/d.D00990642.
ZHU Y J. Design and Implementation of Full Knowledge Map for the Math Problems in Junior High School [D]. Chengdu: University of Electronic Science and Technology of China, 2016. DOI:10.7666/d.D00990642(Chhttp://dx.doi.org/10.7666/d.D00990642(Ch).
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. DOI:10.3969/j.issn.1001-0548.2016.04.012http://dx.doi.org/10.3969/j.issn.1001-0548.2016.04.012.
XU Z L, SHENG Y P, HE L R, et al. Review on knowledge graph techniques[J]. Journal of University of Electronic Science and Technology of China, 2016, 45(4): 589-606. DOI:10.3969/j.issn.1001-0548.2016.04.012(Chhttp://dx.doi.org/10.3969/j.issn.1001-0548.2016.04.012(Ch).
李振, 周东岱, 王勇. “人工智能+”视域下的教育知识图谱:内涵、技术框架与应用研究[J]. 远程教育杂志, 2019, 37(4): 42-53.
LI Z, ZHOU D D, WANG Y. Research of educational knowledge graph from the perspective of “artificial Inte11igence+”: Connotation, technical framework and application[J]. Journal of Distance Education, 2019, 37(4): 42-53(Ch).
VILLALON J, CALVO R A. Concept extraction from student essays, towards concept map mining [C]// Proceedings of the 5th IEEE. Piscataway:IEEE Press,2009:221-225. 10.1109/icalt.2009.215http://dx.doi.org/10.1109/icalt.2009.215
WEN Y, LOOI C K, CHEN W. Appropriation of a representational tool in a second-language classroom [J]. International Journal of Computer Supported Collaborative Learning, 2015, 10(1):77-108. DOI:10.1007/s11412-015-9208-0http://dx.doi.org/10.1007/s11412-015-9208-0.
LIN Y S, CHANG Y C, LIEW K H. Effects of concept map extraction and a test-based diagnostic environment on learning achievement and learners' perceptions [J]. British Journal of Educational Technology,2016,47(4):649-664. DOI: 10.1111/bjet. 12250http://dx.doi.org/10.1111/bjet.12250.
陆泉, 谢祎玉, 陈静, 等. 临床医学课程知识主题图谱构建研究[J]. 图书情报工作, 2019, 63(9): 101-108.
LU Q, XIE Y Y, CHEN J, et al. Research on the construction of clinical medicine course-knowledge topic graph[J]. Library and Information Service, 2019, 63(9): 101-108(Ch).
郭琴芳.基于知识图谱的初中数学在线学习系统及应用[D].西安:西安理工大学,2019.
GUO Q F. Junior High School Online Learning System Based on Knowledge Graph [D]. Xi’an: Xi’an University of Technology, 2019(Ch).
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. DOI:10.7544 /issn1000-1239.2016.20148228http://dx.doi.org/10.7544/issn1000-1239.2016.20148228.
LIU Q, LI Y, DUAN H, et al. Knowledge graph construction techniques[J]. Journal of Computer Research and Development, 2016, 53(3):582-600. DOI:10.7544/issn1000-1239.2016.20148228(Chhttp://dx.doi.org/10.7544/issn1000-1239.2016.20148228(Ch).
HUI B, LIU L, CHEN J,et al. Few-shot relation classification by context attention-based prototypical networks with BERT[J]. EURASIP Journal on Wireless Communications and Networking, 2020, 118:1-17. DOI: 10.1186/s13638-020-01720-6http://dx.doi.org/10.1186/s13638-020-01720-6.
周炫余, 刘娟, 邵鹏, 等. 基于层次过滤模型的中文指代消解[J]. 吉林大学学报(工学版), 2016, 46(4): 1209-1215. DOI: 10.13229/j.cnki.jdxbgxb201604029http://dx.doi.org/10.13229/j.cnki.jdxbgxb201604029.
ZHOU X Y, LIU J, SHAO P, et al. Chinese Anaphora resolution based on multi-pass sieve model [J]. Journal of Jilin University(Engineering and Technology Edition), 2016, 46(4): 1209-1215. DOI: 10.13229/j.cnki.jdxbgxbhttp://dx.doi.org/10.13229/j.cnki.jdxbgxb201604029(Ch).
付洋, 刘茂福, 乔瑞. 心脏病中文知识图谱的构建[J]. 武汉大学学报(理学版), 2020, 66(3): 261-267. DOI: 10. 14188/j.1671-8836.2018.0217http://dx.doi.org/10.14188/j.1671-8836.2018.0217.
FU Y, LIU M F, QIAO R. Construction of Chinese knowledge graph of heart disease [J]. Journal of Wuhan University (Natural Science Edition), 2020, 66(3): 261-267. DOI: 10.14188/j.1671-8836.2018. 0217(Chhttp://dx.doi.org/10.14188/j.1671-8836.2018.0217(Ch).
王雪鹏, 刘康, 何世柱, 等. 基于网络语义标签的多源知识库实体对齐算法[J]. 计算机学报, 2017, 40(3): 701-711. DOI:10.11897/SP.J.1016.2017.00701http://dx.doi.org/10.11897/SP.J.1016.2017.00701.
WANG X P, LIU K, HE S Z, et al. Multi-source knowledge bases entity alignment by leveraging semantic tags[J]. Chinese Journal of Computers, 2017, 40(3): 701-711. DOI: 10.11897/SP.J.1016.2017.00701(Chhttp://dx.doi.org/10.11897/SP.J.1016.2017.00701(Ch).
0
浏览量
51
下载量
3
CSCD
关联资源
相关文章
相关作者
相关机构