计算机工程与应用 ›› 2022, Vol. 58 ›› Issue (1): 56-69.DOI: 10.3778/j.issn.1002-8331.2105-0082
张宇,郭文忠,林森,文朝武,龙洁花
出版日期:
2022-01-01
发布日期:
2022-01-06
ZHANG Yu, GUO Wenzhong, LIN Sen, WEN Chaowu, LONG Jiehua
Online:
2022-01-01
Published:
2022-01-06
摘要: 知识推理作为知识图谱的重要一环,一直处于重点研究热门对象之中。随着深度学习的不断发展,多种深度学习模型与知识推理的结合引起了很大的重视,得到了大量国内外学者的热捧。为了提高从已有知识中推理出新知识的正确率,二者的结合被广泛研究。基于深度学习的知识推理可以挖掘得更深、更仔细、更精确,有效提高了丰富知识库中的实体、关系、属性和文本信息等的利用率,使推理效果更佳。通过简单介绍知识图谱以及知识补全概念,重点叙述知识推理的概念及基本原理,从知识表示学习、知识获取和知识计算应用三个方向展开,综述了基于深度学习的知识推理CTransR、PTransE、TKRL、HAAT、AMNRE、CLSP、HDSA和SDLM模型的最新研究进展;总结了基于深度学习的知识推理在理论、算法和应用方面尚未克服的问题、研究方向和未来发展前景。
张宇, 郭文忠, 林森, 文朝武, 龙洁花. 深度学习与知识推理相结合的研究综述[J]. 计算机工程与应用, 2022, 58(1): 56-69.
ZHANG Yu, GUO Wenzhong, LIN Sen, WEN Chaowu, LONG Jiehua. Review on Combination of Deep Learning and Knowledge Reasoning[J]. Computer Engineering and Applications, 2022, 58(1): 56-69.
[1] 李艳茹,周子力,倪睿康,等.基于知识图谱的学科知识构建[J].计算机时代,2021(4):65-68. LI Y R,ZHOU Z L,NI R K,et al.Construction of subject knowledge graph[J].Computer Era,2021(4):65-68. [2] XLA B,ML A,ZW A,et al.Exploiting knowledge graphs in industrial products and services:A survey of key aspects,challenges,and future perspectives[J].Computers in Industry,2021,129:103449. [3] MAJID A B,BEHROOZ J,BEHROUZ M B.FarsBase-KBP:A knowledge base population system for the persian knowledge graph[J].Journal of Web Semantics,2021,68:100638. [4] 曹永强,齐静威,王菲,等.基于Citespace的作物需水研究知识图谱分析[J].水利经济,2021,39(2):55-62. CAO Y Q,QI J W,WANG F,et al.Knowledge map of Analysis of crop water requirement research based on Citespace[J].Journal of Economics of Water Resources,2021,39(2):55-62. [5] 孙龙龙,王其宽,施凯,等.基于知识图谱的建筑安全领域计算机视觉研究综述[J].安全与环境工程,2021,28(2):44-49. SUN L L,WANG Q G,SHI K,et al.Overview of computer vision research in construction safety field based on knowledge graph[J].Safety and Environmental Engineering,2021,28(2):44-49. [6] DENG W W,MA J.A knowledge graph approach for recommending patents to companies[J].Electronic Commerce Research,2021(9). [7] LIU S,TAN N,GE Y,et al.Research on automatic question answering of generative knowledge graph based on pointer network[J].Information(Switzerland),2021,12(3):136. [8] 龚乐君,杨璐,高志宏,等.LncRNA与疾病关系的知识图谱构建[J].山东大学学报(工学版),2021(2):26-33. GONG L J,YANG L,GAO Z H,et al.Construction of knowledge graph of relationship between LncRNA and diseases[J].Journal of Shandong University(Engineering Science),2021(2):26-33. [9] 杨虎.基于Freebase的英文命名实体识别链接的研究与实现[D].北京:北京邮电大学,2019. YANG H.Research and implementation of english entity discovery and linking system based on freebase[D].Beijing:Beijing University of Posts and Telecommunications,2019. [10] 寇蕾蕾.Wikidata中数据来源分析[J].图书馆理论与实践,2020(4):67-71. KOU L L.Data source analysis in Wikidata[J].Library Theory and Practice,2020(4):67-71. [11] FREIRE N,ROBSON G,HOWARD J B,et al.Cultural heritage metadata aggregation using web technologies:IIIF,Sitemaps and Schema.org[J].International Journal on Digital Libraries,2020,21(1):19-30. [12] AZ A,AUH A,DZ A,et al.KGEL:A novel end-to-end embedding learning framework for knowledge graph completion[J].Expert Systems with Applications,2020,167:114164. [13] 王维美,陈恒,史一民,等.基于卷积神经网络的知识图谱补全方法研究[J].计算机应用与软件,2021,38(4):250-255. WANG W M,CHEN H,SHI Y M,et al.Knowledge graph completion method based on convolutional neural network[J].Computer Application and Software,2021,38(4):250-255. [14] 李忠文,丁烨,花忠云,等.结合三元组重要性的知识图谱补全模型[J].计算机科学,2020,47(11):231-236. LI Z W,DING Y,HUA Z Y,et al.Knowledge graph completion model based on triplet importance integration[J].Computer Science,2020,47(11):231-236. [15] 王硕,杜志娟,孟小峰.大规模知识图谱补全技术的研究进展[J].中国科学(信息科学),2020,50(4):551-575. WANG S,DU Z J,MENG X F. Research progress of large-scale knowledge graph completion technology[J].Science in China(Information Science),2020,50(4):551-575. [16] 崔员宁,李静,陈琰,等.TransPath:一种基于深度迁移强化学习的知识推理方法[J/OL].小型微型计算机系统:1-8[2021?04?18].http://lib.gsdx.gov.cn/asset/detail/0/2031025 152059. CUI Y N,LI J,CHEN Y,et al.TransPath:A deep transfer reinforcement learning method for knowledge reasoning[J/OL].Journal of Chinese Computer Systems:1-8[2021-04-18].http://lib.gsdx.gov.cn/asset/detail/0/2031025152059. [17] 孙建强,许少华.基于可微神经计算机和贝叶斯网络的知识推理方法[J].计算机应用,2021,41(2):337-342. SUN J Q,XU S H.Knowledge reasoning method based on differentiable neural computer and Bayesian network[J].Journal of Computer Applications,2021,41(2):337-342. [18] HUANG F,LI Z,WEI H,et al.Boost image captioning with knowledge reasoning[J].Machine Learning,2020,109:2313-2332. [19] 张清辉,杨楠,梁政.任务驱动的军事信息服务知识推理研究[J].火力与指挥控制,2021,46(5):64-70. ZHANG Q H,YANG N,LIANG Z.Study on knowledge reasoning of task driven military information service[J].Fire Control & Command Control,2021,46(5):64-70. [20] 陈海旭,周强,刘学军.一种结合路径信息和嵌入模型的知识推理方法[J].小型微型计算机系统,2020,41(6):1147-1151. CHEN H X,ZHOU Q,LIU X J.Knowledge graph reasoning combining path information and embedding model[J].Journal of Chinese Computer Systems,2020,41(6):1147-1151. [21] GILGUR A,RAMIREZ-MARQUEZ J E.Using deductive reasoning to identify unhappy communities[J].Social Indicators Research,2020,152:581-605. [22] STEVEN K.Knowledge representation and inductive reasoning using conditional logic and sets of ranking functions[M].[S.l.]:IOS Press,2021-01-25. [23] 孙婧婧,和经纬.作为溯因推理研究方法的因果过程追踪及其在公共政策研究中的应用[J].公共管理评论,2020(4):214-229. SUN J J,HE J W.Causal process tracing as an adductive reasoning method and its application to public policy research[J].China Public Administration Review,2020(4):214-229. [24] YUAN L,UTTAL D H.Analogy lays the foundation for two crucial aspects of symbolic development:intention and correspondence[J].Topics in Cognitive Science,2017,9(3):738. [25] 官赛萍,靳小龙,贾岩涛,等.面向知识图谱的知识推理研究进展[J].软件学报,2018,29(10):2966-2994. GUAN S P,JIN X L,JIA Y T,et al.Knowledge reasoning over knowledge graph:A survey[J].Journal of Software,2018,29(10):2966-2994. [26] 漆桂林,高桓,吴天星.知识图谱研究进展[J].情报工程,2017,3(1):4-25. QI G L,GAO H,WU T X.The research advances of knowledge graph[J].Technology Intelligence Engineering,2017,3(1):4-25. [27] 杨秀璋,武帅,杨琪,等.多视图融合TextRCNN的论文自动推荐算法[J/OL].计算机工程与应用:1-13[2021-10-26].http://kns.cnki.net/kcms/detail/11.2127.TP.20211026.1439. 004.html. YANG X Z,WU S,YANG Q,et al.Automatic paper recommendation algorithm based on multi-view fusion TextRCNN[J/OL].Computer Engineering and Applications:1-13[2021-10-26].http://kns.cnki.net/kcms/detail/11.2127.TP.20211026.1439.004.html. [28] 宋浩楠,赵刚,孙若莹.基于深度强化学习的知识推理研究进展综述[J].计算机工程与应用,2022,58(1):12-25. SONG H N,ZHAO G,SUN R Y.Developments of knowledge reasoning based on deep reinforcement learning[J].Computer Engineering and Applications,2022,58(1): 12-25. [29] 江洋洋,金伯,张宝昌.深度学习在自然语言处理研究进展分析[J].计算机工程与应用,2021,57(22):1-14. JIANG Y Y,JIN B,ZHANG B C.Research progress of natural language processing based on deep learning[J].Computer Engineering and Applications,2021,57(22):1-14. [30] 王乃钰,叶育鑫,刘露,等.基于深度学习的语言模型研究进展[J].软件学报,2021,32(4):1082-1115. WANG N Y,YE Y X,LIU L,et al.Language models based on deep learning:A review[J].Journal of Software,2021,32(4):1082-1115. [31] 赫磊,邵展鹏,张剑华,等.基于深度学习的行为识别算法综述[J].计算机科学,2020,47(Z1):139-147. HE L,SHAO Z P,ZHANG J H,et al.Review of deep learning-based action recognition algorithms[J].Computer Science,2020,47(Z1):139-147. [32] CHEN T T,CHEN Z M,ZHOU Z X.Computational research and implementation of prediction of pork price based on deep learning[J].Journal of Physics(Conference Series),2021,1815(1):012032. [33] 李晓英,杨名,全睿,等.基于深度学习的不均衡文本分类方法[J/OL].吉林大学学报(工学版):1-7[2021-04-18].https://doi.org/10.13229/j.cnki.jdxbgxb20210167. LI X Y,YANG M,QUAN R,et al.Unbalanced text classification method based on deep learning[J/OL].Journal of Jilin University(Engineering and Technology Edition):1-7[2021-04-18].https://doi.org/10.13229/j.cnki.jdxbgxb20210167. [34] 曹志鹏,潘定,潘启亮.基于表示学习的双层知识网络链路预测[J].情报学报,2021,40(2):135-144. CAO Z P,PAN D,PAN Q L.Link prediction in two-layer knowledge network based on network representation learning[J].Journal of the China Society for Scientific and Technical Information,2021,40(2):135-144. [35] 刘知远,韩旭,孙茂松.知识图谱与深度学习[M].北京:清华大学出版社,2020. LIU Z Y,HAN X,SUN M S.Knowledge graph and deep learning[M].Beijing:Tsinghua University Press,2020. [36] MINERVINI P,FANIZZI N,D’AMATO C,et al.Scalable learning of entity and predicate embeddings for knowledge graph completion[C]//Proceedings of IEEE International Conference on Machine Learning & Applications,2016. [37] BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Advances in Neural Information Processing Systems,2013:2787-2795. [38] MOHANNAD A,RACHID B,RICHARD K.Exploiting non-taxonomic relations for measuring semantic similarity and relatedness in WordNet[J].Knowledge-Based Systems,2021,212:106565. [39] SOCHER R,CHEN D,MANNING C D,et al.Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of Advances in Neural Information Processing Systems,2013:926-934. [40] LU M,ILK N,TANG X,et al.Multi-disease prediction using LSTM recurrent neural networks[J].Expert Systems with Applications,2021,177:114905. [41] 刘伟杰,徐杰,吉卫喜,等.面向智能运维的离散制造过程知识获取方法[J].制造业自动化,2019,41(9):56-62. LIU W J,XU J,JI W X,et al.Discrete manufacturing process knowledge acquisition method for intelligent operation and maintenance[J].Manufacturing Automation,2019,41(9):56-62. [42] 吝博强,田文洪.基于层次注意力机制的高效视觉问答模型[J].计算机应用研究,2021,38(2):636-640. LIN B Q,TIAN W H.Efficient image question answering model based on layered attention mechanism[J].Application Research of Computers,2021,38(2):636-640. [43] XU Y A,QIANG Z A,PL A,et al.Fine-grained predicting urban crowd flows with adaptive spatio-temporal graph convolutional network[J].Neurocomputing,2021,446:95-105. [44] GANIN Y,USTINOVA E,AJAKAN H,et al.Domain-adversarial training of neural networks[J].Journal of Machine Learning Research,2017,17(1):2096-2030. [45] MENG F,HUANG K,LI H,et al.Hierarchical class grouping with orthogonal constraint for class activation map generation[J].Neural Computing and Applications,2020(5):1-10. [46] MIKOLOV T,CHEN K,CORRADO G,et al.Efficient estimation of word representations in vector space[J].arXiv:1301.3781v3,2013. [47] 汪舸,吴方君.基于种子词和数据集的垃圾弹幕屏蔽词典的自动构建[J].计算机工程与科学,2020,42(7):1302-1308. WANG G,WU F J.Automatic construction of the garbage barrage shielding dictionary based on seed words and dataset[J].Computer Engineering & Science,2020,42(7):1302-1308. [48] 闫强,张笑妍,周思敏.基于义原相似度的关键词抽取方法[J].数据分析与知识发现,2021,5(4):80-89. YAN Q,ZHANG X Y,ZHOU S M.Extracting keywords based on sememe similarity[J].Data Analysis and Knowledge Discovery,2021,5(4):80-89. [49] BRANDT P M,HERZBERG P Y.Is a cover letter still needed? using LIWC to predict application success[J].International Journal of Selection and Assessment,2020,28(3):417-429. [50] 张信勇.LIWC:一种基于语词计量的文本分析工具[J].西南民族大学学报(人文社会科学版),2015,36(4):101-104. ZHANG X Y.LIWC:A text analysis tool based on word measurement[J].Journal of Southwest Minzu University(Humanities and Social Science),2015,36(4):101-104. [51] COLLADO R A,MOAZENI S.Resource allocation for contingency planning:An inexact bundle method for stochastic optimization[J].SSRN Electronic Journal,2017,291(3):1008-1023. [52] 常立丹,李建国,李博文.基于改进集束搜索的立体车库库位布局优化研究[J].重庆理工大学学报(自然科学),2020,34(11):171-176. CHANG L D,LI J G,LI B W.Research on optimization of stereo garage location based on improved beam search[J].Journal of Chongqing University of Technology(Natural Science),2020,34(11):171-176. [53] 刘丹青.语言单位的义项非独立观[J].世界汉语教学,2021,35(2):147-165. LIU D Q.The non-independence view of sememes of linguistic elements[J].Chinese Teaching in the World,2021,35(2):147-165. [54] JULLUM M.Investigating mesh-based approximation methods for the normalization constant in the log Gaussian Cox process likelihood[J].Stat,2020,9(1):285. [55] 张美玉,林崇,简琤峰.基于路径排序算法的STEP知识推理技术研究[J].浙江工业大学学报,2020,48(2):126-132. ZHANG M Y,LIN C,JIAN Z F.Research on STEP knowledge reasoning technology based on path ranking algorithm[J].Journal of Zhejiang University of Technology,2020,48(2):126-132. [56] LAO N,MINKOV E,COHEN W.Learning relational features with backward random walks[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing,2015. [57] LUIS A G,TEFLIOUDI C,HOSE K,et al.AMIE:Association rule mining under incomplete evidence in ontological knowledge bases[C]//Proceedings of the 22nd International Conference on World Wide Web,2013. [58] 韩慧.基于知识图谱的商品推荐系统[J].信息通信,2020(6):200-201. HAN H.Product recommendation system based on knowledge graph[J].Information & Communications,2020(6):200-201. [59] 朱立国,韩涛,魏戌,等.近十年手法治疗神经根型颈椎病的CiteSpace知识图谱可视化分析[J].中医杂志,2021,62(8):723-728. ZHU L G,HAN T,WEI X,et al.Literated-based knowledge map visualization analysis by CiteSpace:Manipulation treatment for cervical spondylotic radiculopathy[J].Journal of Traditional Chinese Medicine,2021,62(8):723-728. [60] 尤佳琦.我国跨境电商的研究热点与前沿:基于CiteSpace的知识图谱分析[J].新经济,2020(12):94-101. YOU J Q.Research hotspots and frontiers of cross-border E-commerce in China:Knowledge graph analysis based on CiteSpace[J].New Economy,2020(12):94-101. [61] 曹现刚,张梦园,雷卓,等.煤矿装备维护知识图谱构建及应用[J].工矿自动化,2021,47(3):41-45. CAO X G,ZHANG M Y,LEI Z,et al.Construction and application of knowledge graph for coal mine equipment maintenance[J].Industry and Mine Automation,2021,47(3):41-45. [62] 江志浩,周卿,石敏,等.作战目标知识图谱构建与应用[J].海军航空工程学院学报,2020,35(6):471-477. JIANG Z H,ZHOU Q,SHI M,et al.Construction and application of knowledge graph for target in battlefield[J].Journal of Naval Aeronautical and Astronautical University,2020,35(6):471-477. |
[1] | 石颉, 袁晨翔, 丁飞, 孔维相. SAR图像建筑物目标检测研究综述[J]. 计算机工程与应用, 2022, 58(8): 58-66. |
[2] | 熊风光, 张鑫, 韩燮, 况立群, 刘欢乐, 贾炅昊. 改进的遥感图像语义分割研究[J]. 计算机工程与应用, 2022, 58(8): 185-190. |
[3] | 杨锦帆, 王晓强, 林浩, 李雷孝, 杨艳艳, 李科岑, 高静. 深度学习中的单阶段车辆检测算法综述[J]. 计算机工程与应用, 2022, 58(7): 55-67. |
[4] | 王斌, 李昕. 融合动态残差的多源域自适应算法研究[J]. 计算机工程与应用, 2022, 58(7): 162-166. |
[5] | 谭暑秋, 汤国放, 涂媛雅, 张建勋, 葛盼杰. 教室监控下学生异常行为检测系统[J]. 计算机工程与应用, 2022, 58(7): 176-184. |
[6] | 张美玉, 刘跃辉, 侯向辉, 秦绪佳. 基于卷积网络的灰度图像自动上色方法[J]. 计算机工程与应用, 2022, 58(7): 229-236. |
[7] | 张壮壮, 屈立成, 李翔, 张明皓, 李昭璐. 基于时空卷积神经网络的数据缺失交通流预测[J]. 计算机工程与应用, 2022, 58(7): 259-265. |
[8] | 许杰, 祝玉坤, 邢春晓. 基于深度强化学习的金融交易算法研究[J]. 计算机工程与应用, 2022, 58(7): 276-285. |
[9] | 张昊, 张小雨, 张振友, 李伟. 基于深度学习的入侵检测模型综述[J]. 计算机工程与应用, 2022, 58(6): 17-28. |
[10] | 王鑫鹏, 王晓强, 林浩, 李雷孝, 杨艳艳, 孟闯, 高静. 深度学习典型目标检测算法的改进综述[J]. 计算机工程与应用, 2022, 58(6): 42-57. |
[11] | 陈嘉涛, 张泓凯, 黄燕平, 蓝公仆, 许景江, 秦嘉, 安林. 基于视频的生理参数测量技术及研究进展[J]. 计算机工程与应用, 2022, 58(6): 58-68. |
[12] | 汪晶, 王恺, 严迎建. 基于条件生成对抗网络的侧信道攻击技术研究[J]. 计算机工程与应用, 2022, 58(6): 110-117. |
[13] | 闫志豪, 刘京菊, 郭徽, 郭兵阳. 基于域名系统知识图谱的CDN域名识别技术[J]. 计算机工程与应用, 2022, 58(6): 149-156. |
[14] | 李彦辰, 张小俊, 张明路, 沈亮屹. 基于改进Efficientdet的自动驾驶场景目标检测[J]. 计算机工程与应用, 2022, 58(6): 183-191. |
[15] | 张振伟, 郝建国, 黄健, 潘崇煜. 小样本图像目标检测研究综述[J]. 计算机工程与应用, 2022, 58(5): 1-11. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||