知识图谱构建技术综述

doi:10.19678/j.issn.1000-3428.0061803

摘要/Abstract

摘要： 知识图谱在医疗、金融、农业等领域得到快速发展与广泛应用，其可以高效整合海量数据的有效信息，为实现语义智能化搜索以及知识互联打下基础。随着深度学习的发展，传统基于规则和模板的知识图谱构建技术已经逐渐被深度学习所替代。梳理知识抽取、知识融合、知识推理3类知识图谱构建技术的发展历程，重点分析基于卷积神经网络、循环神经网络等深度学习的知识图谱构建方法，并归纳现有方法的优劣性与发展思路。此外，深度学习虽然在自然语言处理、计算机视觉等领域取得了较大成果，但自身存在依赖大规模样本、缺乏推理性与可解释性等缺陷，限制了其进一步发展。为此，对知识图谱应用于深度学习以改善深度学习自身缺陷的相关方法进行整理，分析深度学习的可解释性、指导性以及因果推理性，归纳知识图谱的优势以及发展的必要性。在此基础上，对知识图谱构建技术以及知识图谱应用于深度学习所面临的困难和挑战进行梳理和分析，并对该领域的发展前景加以展望。

关键词: 知识图谱, 信息抽取, 语义网, 深度学习, 自然语言处理

Abstract: Knowledge graph has been rapidly developed and widely used in the medical, financial, agricultural, and other fields.It can efficiently integrate the effective information of massive data and lay the foundation for semantic intelligent search and knowledge interconnection.With the development of deep learning, the traditional knowledge graph construction technology based on rules and templates has been gradually replaced by deep learning.This paper studies the development process of three types of knowledge graph construction technologies:knowledge extraction, knowledge fusion, and knowledge reasoning;focuses on knowledge graph construction methods based on deep learning such as Convolutional Neural Network(CNN) and Recurrent Neural Network(RNN);and summarizes the advantages and disadvantages of existing methods and development ideas.In addition, although deep learning has made great achievements in Natural Language Processing(NLP), computer vision, and other fields, its own defects such as reliance on large-scale samples, lack of reasoning, and interpretability limit its further development.Therefore, this paper sorts out the relevant methods for applying knowledge graph to deep learning to address the defects of the latter;analyzes the interpretability, guidance, and causal reasoning of deep learning;and summarizes the advantages of knowledge graph and the necessity of development.On this basis, this paper studies and analyzes the construction technology of knowledge graph and the difficulties and challenges faced by the application of knowledge graph in deep learning and looks forward to the development prospect of this field.

Key words: knowledge graph, information extraction, semantic Web, deep learning, Natural Language Processing(NLP)

中图分类号:

TP391.1

张吉祥, 张祥森, 武长旭, 赵增顺. 知识图谱构建技术综述[J]. 计算机工程, 2022, 48(3): 23-37.

ZHANG Jixiang, ZHANG Xiangsen, WU Changxu, ZHAO Zengshun. Survey of Knowledge Graph Construction Techniques[J]. Computer Engineering, 2022, 48(3): 23-37.

http://www.ecice06.com/CN/Y2022/V48/I3/23

图/表 12

20220330200336

20220330200340

20220330200344

20220330200348

20220330200351

20220330200355

20220330200359

20220330200404

20220330200408

20220330200411

20220330200415

20220330200419

参考文献

[1] MIN C, MAO S, LIU Y.Big data:a survey[J].Mobile Networks & Applications, 2014, 19(2):171-209.
[2] 付小红.论知识组织的原则[J].情报资料工作, 2001(5):11-15. FU X H.Principles on knowledge organization[J].Information and Documentation Services, 2001(5):11-15.(in Chinese)
[3] 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 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.(in Chinese)
[4] 李涓子, 侯磊.知识图谱研究综述[J].山西大学学报(自然科学版), 2017, 40(3):454-459. LI J Z, HOU L.Reviews on knowledge graph research[J].Journal of Shanxi University(Natural Science Edition), 2017, 40(3):454-459.(in Chinese)
[5] Al-MOSLMI T, OCAA M G, OPDAHL A L, et al.Named entity extraction for knowledge graphs:a literature overview[J].IEEE Access, 2020, 8:32862-32881.
[6] SMIRNOVA A, CUDRE-MAUROUX P.Relation extraction using distant supervision:a survey[J].ACM Computing Surveys, 2019, 51(5):1-35.
[7] KUMAR S.A survey of deep learning methods for relation extraction[EB/OL].[2021-04-05].https://arxiv.org/pdf/1705.03645.pdf.
[8] 庄传志, 靳小龙, 朱伟建, 等.基于深度学习的关系抽取研究综述[J].中文信息学报, 2019, 33(12):1-18. ZHUANG C Z, JIN X L, ZHU W J, et al.Deep learning based relation extraction:a survey[J].Journal of Chinese Information Processing, 2019, 33(12):1-18.(in Chinese)
[9] DONG X, GABRILOVICH E, HEITZ G, et al.Knowledge vault:a Web-scale approach to probabilistic knowledge fusion[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York, USA:ACM Press, 2014:601-610.
[10] HAO Y, ZHANG Y, LIU K, et al.An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.[S.l.]:ACL, 2017:221-231.
[11] GONG F, WANG M, WANG H, et al.SMR:medical knowledge graph embedding for safe medicine recommendation[J].Big Data Research, 2021, 23:100174.
[12] 王昊奋, 漆桂林, 陈华钧.知识图谱:方法, 实践与应用[M].北京:电子工业出版社, 2019. WANG H F, QI G L, CHEN H J.Knowledge graph:method, practice and application[M].Beijing:Publishing House of Electronics Industry, 2019.(in Chinese)
[13] RAU L F.Extracting company names from text[C]//Proceedings of the 7th IEEE Conference on Artificial Intelligence Applications.Washington D.C., USA:IEEE Press, 1991:12-23.
[14] HUMPHREYS K, GAIZAUSKAS R, AZZAM S, et al.University of sheffield:description of the LaSIE-II system as used for MUC-7[M].[S.l.]:Association for Computational Linguistics, 1998.
[15] AITKEN J S.Learning information extraction rules:an inductive logic programming approach[C]//Proceedings of the 15th European Conference on Artificial Intelligence.Berlin, Germany:Springer, 2002:102-112.
[16] SCHUTZ A, BUITELAAR P.RelExt:a tool for relation extraction from text in ontology extension[C]//Proceedings of the 4th International Semantic Web Conference.Berlin, Germany:Springer, 2005:593-606.
[17] ZHOU G D, ZHANG J, SU J, et al.Recognizing names in biomedical texts:a machine learning approach[EB/OL].[2021-04-05].https://academic.oup.com/bioinformatics/article/20/7/1178/245780.
[18] LIU X, ZHANG S, WEI F, et al.Recognizing named entities in tweets[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics.[S.l.]:ACL, 2011:14-18.
[19] SHINYAMA Y, SEKINE S.Preemptive information extraction using unrestricted relation discovery[C]//Proceedings of Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics.[S.l.]:ACL, 2006:304-311.
[20] MA X, HOVY E.End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF[EB/OL].[2021-04-05].https://www.aclweb.org/old_anthology/P/P16/P16-1101.pdf.
[21] 杨飘, 董文永.基于BERT嵌入的中文命名实体识别方法[J].计算机工程, 2020, 46(4):40-45, 52. YANG P, DONG W Y.Chinese named entity recognition method based on BERT embedding[J].Computer Engineering, 2020, 46(4):40-45, 52.(in Chinese)
[22] GAN T, GAN Y, YANMIN H E.Subsequence-level entity attention LSTM for relation extraction[C]//Proceedings of 2019 International Computer Conference on Wavelet Active Media Technology and Information Processing.Washington D.C., USA:IEEE Press, 2019:102-113.
[23] XIAO J, ZHOU Z.Chapter-level entity relationship extraction method based on joint learning[C]//Proceedings of 2020 International Conference on Intelligent Human-Machine Systems and Cybernetics.Washington D.C., USA:IEEE Press, 2020:145-156.
[24] RONAN C, JASON W, LÉON B, et al.Natural language processing(almost) from scratch[J].Journal of Machine Learning Research, 2011, 12:2493-2537.
[25] QIU J, ZHOU Y, WANG Q, et al.Chinese clinical named entity recognition using residual dilated convolutional neural network with conditional random field[J].IEEE Transactions on NanoBioscience, 2019, 12:306-315.
[26] KONG J, ZHANG L, JIANG M, et al.Incorporating multi-level CNN and attention mechanism for Chinese clinical named entity recognition[J].Journal of Biomedical Informatics, 2021, 116:103737.
[27] HUANG Z, WEI X, KAI Y.Bidirectional LSTM-CRF models for sequence tagging[EB/OL].[2021-04-05].https://arxiv.org/pdf/1508.01991.pdf.
[28] UKOV-GREGORI A, BACHRACH Y, COOPE S.Named entity recognition with parallel recurrent neural networks[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.[S.l.]:ACL, 2018:69-74.
[29] RONRAN C, LEE S.Effect of character and word features in bidirectional LSTM-CRF for NER[C]//Proceedings of 2020 IEEE International Conference on Big Data and Smart Computing.Washington D.C., USA:IEEE Press, 2020:14-25.
[30] YAN H, DENG B, LI X, et al.TENER:adapting transformer encoder for name entity recognition[EB/OL].[2021-04-05].https://arxiv.org/pdf/1911.04474.pdf.
[31] DEVLIN J, CHANG M W, LEE K, et al.BERT:pre-training of deep bidirectional transformers for language understanding[EB/OL].[2021-04-05].https://aclanthology.org/N19-1423.pdf.
[32] 曾青霞, 熊旺平, 杜建强, 等.结合自注意力的BiLSTM-CRF的电子病历命名实体识别[J].计算机应用与软件, 2021, 38(3):159-162, 242. ZENG Q X, XIONG W P, DU J Q, et al.Electronic medical record named entity recognition combined with self-attention BiLSTM-CRF[J].Computer Applications and Software, 2021, 38(3):159-162, 242.(in Chinese)
[33] 罗熹, 夏先运, 安莹, 等.结合多头自注意力机制与BiLSTM-CRF的中文临床实体识别[J].湖南大学学报(自然科学版), 2021, 48(4):45-55. LUO X, XIA X Y, AN Y, et al.Chinese CNER combined with multi-head self-attention and BiLSTM-CRF[J].Journal of Human University(Natural Sciences), 2021, 48(4):45-55.(in Chinese)
[34] 于浏洋, 郭志刚, 陈刚, 等.面向知识图谱构建的知识抽取技术综述[J].信息工程大学学报, 2020, 21(2):227-235. YU L Y, GUO Z G, CHEN G, et al.Summary of knowledge graph construction oriented knowledge extraction technology[J].Journal of Information Engineering University, 2020, 21(2):227-235.(in Chinese)
[35] ZENG D, LIU K, LAI S, et al.Relation classification via convolutional deep neural network[EB/OL].[2021-04-05].http://www.nlpr.labs.gov.cn/cip/liukang.files/camera_coling2014_final.pdf.
[36] XU K, FENG Y, HUANG S, et al.Semantic relation classification via convolutional neural networks with simple negative sampling[J].Computer Science, 2015, 71:941-949.
[37] GUO X Y, ZHANG H Y, XU H J, et al.A single attention-based combination of CNN and RNN for relation classification[J].IEEE Access, 2019, 7:12467-12475.
[38] 闫雄, 段跃兴, 张泽华.采用自注意力机制和CNN融合的实体关系抽取[J].计算机工程与科学, 2020, 42(11):2059-2066. YAN X, DUAN Y X, ZHANG Z H.Entity relationship extraction fusing self-attention mechanism and CNN[J].Computer Engineering & Science, 2020, 42(11):2059-2066.(in Chinese)
[39] 龚乐君, 刘晓林, 高志宏, 等.基于双向GRU和CNN的药物相互作用关系抽取[J].陕西师范大学学报(自然科学版), 2020, 48(6):108-113. GONG L J, LIU X L, GAO Z H, et al.Extraction of drug-drug interaction based on bidirectional GRU and CNN[J].Journal of Shaanxi Normal University(Natural Science Edition), 2020, 48(6):108-113.(in Chinese)
[40] YIN B, SUN Y, WANG Y.Entity relation extraction method based on fusion of multiple information and attention mechanism[C]//Proceedings of 2020 IEEE International Conference on Computer and Communications.Washington D.C., USA:IEEE Press, 2020:145-160.
[41] SOCHER R, HUVAL B, MANNING C D, et al.Semantic compositionality through recursive matrix-vector spaces[C]//Proceedings of Joint Conference on Empirical Methods in Natural Language Processing(EMNLP) & Computational Natural Language Learning(CoNLL).Washington D.C., USA:IEEE Press, 2012:1201-1211.
[42] SHU Z, ZHENG D, HU X, et al.Bidirectional long short-term memory networks for relation classification[C]//Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation.Washington D.C., USA:IEEE Press, 2015:73-78.
[43] GENG Z, CHEN G, HAN Y, et al.Semantic relation extraction using sequential and tree-structured LSTM with attention[J].Information Sciences, 2020, 509:183-192.
[44] 张勇, 高大林, 巩敦卫, 等.用于关系抽取的注意力图长短时记忆神经网络[J].智能系统学报, 2021, 16(3):518-527. ZHANG Y, GAO D L, GONG D W, et al.Attention graph long short term memory neural network for relation extraction[J].CAAI Transactions on Intelligent Systems, 2021, 16(3):518-527.(in Chinese)
[45] MIWA M, BANSAL M.End-to-end relation extraction using LSTMs on sequences and tree structures[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.[S.l.]:ACL, 2016:1105-1116.
[46] KATIYAR A, CARDIE C.Going out on a limb:joint extraction of entity mentions and relations without dependency trees[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.[S.l.]:ACL, 2017:917-928.
[47] ZHENG S, WANG F, BAO H, et al.Joint extraction of entities and relations based on a novel tagging scheme[EB/OL].[2021-04-05].https://arxiv.org/pdf/1706.05075.pdf.
[48] LIU Y, LI A, HUANG J, et al.Joint extraction of entities and relations based on multi-label classification[C]//Proceedings of 2019 IEEE International Conference on Data Science in Cyberspace.Washington D.C., USA:IEEE Press, 2019:102-113.
[49] WEI Z, SU J, WANG Y, et al.A novel hierarchical binary tagging framework for relational triple extraction[EB/OL].[2021-04-05].https://arxiv.org/pdf/1909.03227v2.pdf.
[50] WANG C, LI A, TU H, et al.An advanced BERT-based decomposition method for joint extraction of entities and relations[C]//Proceedings of 2020 IEEE International Conference on Data Science in Cyberspace.Washington D.C., USA:IEEE Press, 2020:145-163.
[51] 林海伦, 王元卓, 贾岩涛, 等.面向网络大数据的知识融合方法综述[J].计算机学报, 2017, 40(1):1-27. LIN H L, WANG Y Z, JIA Y T, et al.Network big data oriented knowledge fusion methods:a survey[J].Chinese Journal of Computers, 2017, 40(1):1-27.(in Chinese)
[52] KALFOGLOU Y, SCHORLEMMER M.Ontology mapping:the state of the art[J].The Knowledge Engineering Review, 2003, 18(1):1-31.
[53] PINTO H S, MARTINS J P.A methodology for ontology integration[C]//Proceedings of the 1st International Conference on Knowledge Capture.Washington D.C., USA:IEEE Press, 2001:123-146.
[54] PORTER M F.An algorithm for suffix stripping[J].Program Electronic Library and Information Systems, 1980, 14(3):130-137.
[55] NOY N F, MUSEN M A.The PROMPT suite:interactive tools for ontology merging and mapping[J].International Journal of Human-Computer Studies, 2003, 59(6):983-1024.
[56] NEWCOMBE H B, KENNEDY J M, AXFORD S J, et al.Automatic linkage of vital records[J].Science, 1959, 130(3381):954-959.
[57] 张伟莉, 黄廷磊, 梁霄.基于半监督协同训练的百科知识库实体对齐[J].计算机与现代化, 2017(12):88-93. ZHANG W L, HUANG T L, LIANG X.Instance alignment algorithm between encyclopedia based on semi-supervised co-training[J].Computer and Modernization, 2017(12):88-93.(in Chinese)
[58] LI J, WANG Z, XIAO Z, et al.Large scale instance matching via multiple indexes and candidate selection[J].Knowledge-Based Systems, 2013, 50:112-120.
[59] BHATTACHARYA I, GETOOR L.Collective entity resolution in relational data[J].ACM Transactions on Knowledge Discovery from Data, 2007, 1(1):5-10.
[60] LACOSTE-JULIEN S, PALLA K, DAVIES A, et al.SiGMa:simple greedy matching for aligning large knowledge bases[C]//Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York, USA:ACM Press, 2013:10-13.
[61] WICK M, SINGH S, MCCALLUM A.A discriminative hierarchical model for fast coreference at large scale[C]//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics.[S.l.]:ACL, 2012:379-388.
[62] RASTOGI V, DALVI N, GAROFALAKIS M.Large-scale collective entity matching[J].Proceedings of the VLDB Endowment, 2011, 4(4):208-218.
[63] SCHOENMACKERS S, DAVIS J, ETZIONI O, et al.Learning first-order horn clauses from Web text[C]//Proceedings of Conference on Empirical Methods in Natural Language Processing.New York, USA:ACM Press, 2010:1088-1098.
[64] CHEN Y, GOLDBERG S, WANG D Z, et al.Ontological pathfinding:mining first-order knowledge from large knowledge bases[C]//Proceedings of 2016 ACM SIGMOD Conference on Management of Data.New York, USA:ACM Press, 2016:835-846.
[65] 刘峤, 韩明皓, 江浏祎, 等.基于双层随机游走的关系推理算法[J].计算机学报, 2017, 40(6):1275-1290. LIU Q, HAN M H, JIANG L Y, et al.Two-tier random walk based relational inference algorithm[J].Chinese Journal of Computers, 2017, 40(6):1275-1290.(in Chinese)
[66] WANG C, CHENG P.Translating representations of knowledge graphs with neighbors[C]//Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval.New York, USA:ACM Press, 2018:917-920.
[67] SUN Z Q, DENG Z H, NIE J Y, et al.Rotate:knowledge graph embedding by relational rotation in complex space[EB/OL].[2021-04-05].http://arxiv.org/pdf/1902.10197.pdf.
[68] 彭敏, 黄婷, 田纲, 等.聚合邻域信息的联合知识表示模型[J].中文信息学报, 2021, 35(5):46-54. PENG M, HUANG T, TIAN G, et al.Neighborhood aggregation for knowledge graph representation[J].Journal of Chinese Information Processing, 2021, 35(5):46-54.(in Chinese)
[69] 宋浩楠, 赵刚, 王兴芬.融合知识表示和深度强化学习的知识推理方法[J].计算机工程与应用, 2021, 57(19):189-197. SONG H N, ZHAO G, WANG X F, et al.Knowledge reasoning method combining knowledge representation with deep reinforcement learning[J].Computer Engineering and Applications, 2021, 57(19):189-197.(in Chinese)
[70] NICKEL M, TRESP V, KRIEGEL H P.A three-way model for collective learning on multi-relational data[C]//Proceedings of International Conference on Machine Learning.Washington D.C., USA:IEEE Press, 2011:809-816.
[71] CHANG K W, YIH W T, YANG B, et al.Typed tensor decomposition of knowledge bases for relation extraction[EB/OL].[2021-04-05].https://mirror.aclweb.org/emnlp2014/papers/pdf/EMNLP2014165.pdf.
[72] 吴运兵, 朱丹红, 廖祥文, 等.路径张量分解的知识图谱推理算法[J].模式识别与人工智能, 2017, 30(5):473-480. WU Y B, ZHU D H, LIAO X W, et al.Knowledge graph reasoning based on paths of tensor factorization[J].Pattern Recognition and Artificial Intelligence, 2017, 30(5):473-480.(in Chinese)
[73] YANG B, YIH W T, HE X, et al.Embedding entities and relations for learning and inference in knowledge bases[EB/OL].[2021-04-05].http://scottyih.org/files/ICLR2015_updated.pdf.
[74] 刘峤, 韩明皓, 杨晓慧, 等.基于表示学习和语义要素感知的关系推理算法[J].计算机研究与发展, 2017, 54(8):1682-1692. LIU Q, HAN M H, YANG X H, et al.Representation learning based relational inference algorithm with semantical aspect awareness[J].Journal of Computer Research and Development, 2017, 54(8):1682-1692.(in Chinese)
[75] ZHANG S, TAY Y, YAO L N, et al.Quaternion knowledge graph embeddings[C]//Proceedings of the 33rd Conference on Neural Information Processing Systems.New York, USA:ACM Press, 2019:2731-2741.
[76] SOCHER R, CHEN D, 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.New York, USA:ACM Press, 2013:926-930.
[77] DAS R, NEELAKANTAN A, BELANGER D, et al.Chains of reasoning over entities, relations, and text using recurrent neural networks[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics.[S.l.]:ACL, 2017:105-110.
[78] GUO L B, ZHANG Q H, GE W Y, et al.DSKG:a deep sequential model for knowledge graph completion[C]//Proceedings of 2018 China Conference on Knowledge Graph and Semantic Computing.Berlin, Germany:Springer, 2018:65-77.
[79] CHEN W R, HONG D P, ZHENG C.Learning knowledge graph embedding with entity descriptions based on LSTM networks[C]//Proceedings of 2020 IEEE International Symposium on Product Compliance Engineering-Asia.Washington D.C., USA:IEEE Press, 2020:1-7.
[80] DETTMERS T, MINERVINI P, STENETORP P, et al.Convolutional 2D knowledge graph embeddings[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence.[S.l.]:AAAI Press, 2017:1811-1818.
[81] VASHISHTH S, SANYAL S, NITIN V, et al.InteractE:improving convolution-based knowledge graph embeddings by increasing feature interactions[C]//Proceedings of AAAI Conference on Artificial Intelligence.[S.l.]:AAAI Press, 2020:3009-3016.
[82] 李少杰, 陈曙东, 郝悦星, 等.基于卷积神经网络的高效知识表示模型[J].高技术通讯, 2020, 30(9):901-907. LI S J, CHEN S D, HAO Y X, et al.A novel knowledge representation model based on convolutional neural network[J].Chinese High Technology Letters, 2020, 30(9):901-907.(in Chinese)
[83] CATHERINE R, COHEN W.Personalized recommendations using knowledge graphs:a probabilistic logic programming approach[C]//Proceedings of ACM Conference on Recommender Systems.New York, USA:ACM Press, 2016:11-22.
[84] CAO Y, XIANG W, HE X, et al.Unifying knowledge graph learning and recommendation:towards a better understanding of user preferences[EB/OL].[2021-04-05].https://arxiv.org/pdf/1902.06236.pdf.
[85] ZHANG Q, CAO R, SHI F, et al.Interpreting CNN knowledge via an explanatory graph[EB/OL].[2021-04-05].https://arxiv.org/pdf/1708.01785.pdf.
[86] HU Z, MA X, LIU Z, et al.Harnessing deep neural networks with logic rules[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.[S.l.]:ACL, 2016:2410-2420.
[87] WANG H, POON H.Deep probabilistic logic:a unifying framework for indirect supervision[EB/OL].[2021-04-05].https://arxiv.org/pdf/1808.08485.pdf.
[88] LI T, SRIKUMAR V.Augmenting neural networks with first-order logic[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.[S.l.]:ACL, 2019:102-113.
[89] WANG W, PAN S J.Integrating deep learning with logic fusion for information extraction[EB/OL].[2021-04-05].https://arxiv.org/pdf/1912.03041v1.pdf.
[90] PEARL J.Theoretical impediments to machine learning with seven sparks from the causal revolution[C]//Proceedings of the 7th ACM International Conference on Web Search and Data Mining.New York, USA:ACM Press, 2018:3-9.
[91] BATTAGLIA P W, HAMRICK J B, BAPST V, et al.Relational inductive biases, deep learning, and graph networks[EB/OL].[2021-04-05].https://arxiv.org/pdf/1806.01261.pdf.
[92] 康雁, 李涛, 李浩, 等.融合知识图谱与协同过滤的推荐模型[J].计算机工程, 2020, 46(12):73-79, 87. KANG Y, LI T, LI H, et al.Recommendation model fusing with knowledge graph and collaborative filtering[J].Computer Engineering, 2020, 46(12):73-79, 87.(in Chinese)
[93] PAREJA A, DOMENICONI G, CHEN J, et al.EvolveGCN:evolving graph convolutional networks for dynamic graphs[EB/OL].[2021-04-05].https://arxiv.org/pdf/1902.10191.pdf.

选择文件类型/文献管理软件名称

选择包含的内容