时态知识图谱补全的方法及其进展

doi:10.11959/j.issn.2096-0271.2021024

摘要/Abstract

摘要：

时态知识图谱是将时间信息添加到传统的知识图谱而得到的。近年来，时态知识图谱补全受到了学术界的高度关注，并成为研究热点之一。总结了目前时态知识图谱补全的两大类方法，即基于符号逻辑的方法和基于知识表示学习的方法，比较分析了两类方法的优缺点，展望了未来时态补全方法的发展方向，还总结了7个用于时态知识图谱补全的基准数据集和若干代表性模型在基准数据集上的评测结果。

关键词: 时态知识图谱, 本体, 表示学习

Abstract:

Temporal knowledge graph (TKG) are obtained by adding the time information of real-world knowledge to classical knowledge graphs.Recently, TKG completion has drawn much attention and become a hot topic in research.Two main methodologies for TKG completion were summarized, one based on symbolic logic whereas and the other based on knowledge representation learning.The pros and cons of these two different methodologies were discussed, highlighting some directions for enhancing TKG completion in future research.Also, seven benchmark datasets for TKG completion and evaluation results of several typical models on the benchmark datasets were introduced.

Key words: temporal knowledge graph, ontology, representation learning

中图分类号:

TP18

申宇铭, 杜剑峰. 时态知识图谱补全的方法及其进展[J]. 大数据, 2021, 7(3): 30-41.

Yuming SHEN, Jianfeng DU. Temporal knowledge graph completion:methods and progress[J]. Big Data Research, 2021, 7(3): 30-41.

图/表 5

图1

图2

图3

表1

表2

参考文献 42

[1]	LEETARU K , SCHRODT P . GDELT:global data on events,location and tone,19792012[C]// Proceedings of the ISA 2013 Annual Convention.[S.l.:s.n.], 2013: 1-49.
[2]	BOSCHEE E , LAUTENSCHLAGER J , BRIEN S ,et al. ICEWS coded event data[Z]. 2015.
[3]	KAZEMI S M , GOEL R , JAIN K ,et al. Representation learning for dynamic graphs:a survey[J]. Journal of Machine Learning Research, 2020,21(70): 1-73.
[4]	BAADER F , BORGWARDT S , LIPPMANN M . Temporal query entailment in the description logic SHQ[J]. Journal of Web Semantics, 2015,33(8): 71-93.
[5]	BORGWARDT S , THOST V . Temporal conjunctive query answering in the extended DL-Lite family[J]. arXiv preprint, 2020,arXiv:2003.09508.
[6]	BORGWARDT S , THOST V . Temporal query answering in the description logic EL[C]// Proceedings of the 24th Joint Conference on Artificial Intelligence (IJCAI).[S.l.:s.n.], 2015: 2819-2825.
[7]	ARTALE A , KONTCHAKOV R , WOLTER F ,et al. Temporal description logic for ontologybased data access[C]// Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI).[S.l.:s.n.], 2013: 711-717.
[8]	GUTIéRREZ-BASULTO V , JUNG J C , SCHNEIDER T . Lightweight temporal description logics with rigid roles and restricted TBoxes[C]// Proceedings of the 24th Joint Conference on Artificial Intelligence (IJCAI).[S.l.:s.n.], 2015: 3015-3021.
[9]	ARTALE A , KONTCHAKOV R , KOVTUNOVA A ,et al. First-order rewritability of ontology-mediated queries in linear temporal logic[J]. arXiv preprint, 2020,arXiv:2004.07221.
[10]	BORDES A , USUNIER N , GARCíADURáN A ,et al. Translating embeddings for modeling multi-relational data[C]// Proceedings of the 26th Annual Conference on Neural Information Processing Systems (NIPS).[S.l.]: Curran Associates Inc., 2013: 2787-2795.
[11]	WANG Z , ZHANG J W , FENG J L ,et al. Knowledge graph embedding by translating on hyperplanes[C]// Proceedings of the 28th AAAI Conference on Artificial Intelligence (AAAI). Palo Alto:AAAI Press, 2014: 1112-1119.
[12]	LIN Y K , LIU Z Y , SUN M S ,et al. Learning entity and relation embeddings for knowledge graph completion[C]// Proceedings of the 29th AAAI Conference on Artificial Intelligence(AAAI). Palo Alto:AAAI Press, 2015: 2181-2187.
[13]	JI G L , HE S Z , XU L H ,et al. Knowledge graph embedding via dynamic mapping matrix[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL).[S.l]: Association for Computational Linguistics, 2015: 687-696.
[14]	XIAO H , HUANG M L , ZHU X . TransG:a generative model for knowledge graph embedding[C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL).[S.l]: Association for Computational Linguistics, 2016: 992-998.
[15]	SUN Z Q , DENG Z H , NIE J Y ,et al. RotatE:knowledge graph embedding by relational rotation in complex space[C]// Proceedings of the 7th International Conference on Learning Representations (ICLR).[S.l:s.n.], 2019.
[16]	NICKEL M , TRESP V , KRIEGEL H . A three-way model for collective learning on multi-relational data[C]// Proceedings of the 28th International Conference on Machine Learning (ICML). Madison:Omnipress, 2011: 809-816.
[17]	NICKEL M , ROSASCO L , POGGIO T . Holographic embeddings of knowledge graphs[C]// Proceedings of the 30th AAAI Conference on Artificial Intelligence (AAAI). Palo Alto:AAAI Press, 2016: 1955-1961.
[18]	YANG B S , YIH W , HE X D ,et al. Embedding entities and relations for learning and inference in knowledge bases[C]// Proceedings of the 3rd International Conference on Learning Representations (ICLR).[S.l:s.n.], 2015.
[19]	TROUILLON T , WELBL J , RIEDEL S ,et al. Complex embeddings for simple link prediction[C]// Proceedings of the 33nd International Conference on Machine Learning (ICML). Madison:Omnipress, 2016: 2071-2080.
[20]	LIU H X , WU Y X , YANG Y M . Analogical inference for multi-relational embeddings[C]// Proceedings of the 34th International Conference on Machine Learning (ICML). Madison:Omnipress, 2017: 2168-2178.
[21]	KAZEMI S M , POOLE D . Simple embedding for link prediction in knowledge graphs[C]// Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS).[S.l.]: Curran Associates Inc., 2018: 4289-4300.
[22]	BALA?EVI? I , ALLEN C , HOSPEDALES T . Tucker:tensor factorization for knowledge graph completion[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP).[S.l]: Association for Computational Linguistics, 2019: 5185-5194.
[23]	BORDES A , GLOROT X , WESTON J ,et al. A semantic matching energy function for learning with multi-relational data - application to word-sense disambiguation[J]. Machine Language, 2014,94(2): 233-259.
[24]	SOCHER R , CHEN D Q , MANNING C D ,et al. Reasoning with neural tensor networks for knowledge base completion[C]// Proceedings of 27th Annual Conference on Neural Information Processing Systems (NIPS).[S.l.]: Curran Associates Inc., 2013: 926-934.
[25]	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:ACM Press, 2014: 601-610.
[26]	JIANG T S , LIU T Y , GE T ,et al. Towards time-aware knowledge graph completion[C]// Proceedings of the 26th International Conference on Computational Linguistics (COLING).[S.l.:s.n.], 2016: 1715-1724.
[27]	DASGUPTA S S , RAY S N , TALUKDAR P . HyTE:hyperplane-based temporally aware knowledge graph embedding[C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP).[S.l]: Association for Computational Linguistics, 2018: 2001-2011.
[28]	MA Y P , TRESP V , DAXBERGER E A . Embedding models for episodic knowledge graphs[J]. Journal of Web Semantics, 2018,59.
[29]	LACROIX T , OBOZINSKI G , USUNIER N . Tensor decompositions for temporal knowledge base completion[C]// Proceedings of the 8th International Conference on Learning Representations (ICLR).[S.l:s.n.], 2020.
[30]	JAIN P , RATHI S , MAUSAM M . Temporal knowledge base completion:new algorithms and evaluation protocols[C]// Proceedings of the 2020 International Conference on Empirical Methods in Natural Language Processing (EMNLP).[S.l]: Association for Computational Linguistics, 2020: 3733-3747.
[31]	XU C J , NAYYERI M , ALKHOURY F ,et al. TeRo:a time-aware knowledge graph embedding via temporal rotation[C]// Proceedings of the 28th International Conference on Computational Linguistics (COLING).[S.l.:s.n.], 2020: 1583-1593.
[32]	GARCIA-DURAN A , DUMANCIC S , NIEPERT M . Learning sequence encoders for temporal knowledge graph completion[C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP).[S.l]: Association for Computational Linguistics, 2018: 4816-4821.
[33]	GOEL R , KAZEMI S M , BRUBAKER M ,et al. Diachronic embedding for temporal knowledge graph completion[C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI). Palo Alto:AAAI Press, 2020: 3988-3995.
[34]	WU J P , CAO M , CHEUNG J C K ,et al. TeMP:temporal message passing for temporal knowledge graph completion[C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).[S.l]: Association for Computational Linguistics, 2020: 5730-5746.
[35]	JUNG J , JUNG J , KANG U . T-GAP:learning to walk across time for temporal knowledge graph completion[J]. arXiv preprint, 2020,arXiv:2012.10595.
[36]	XU Y R , E H H , SONG M N ,et al. RTFE:a recursive temporal fact embedding framework for temporal knowledge graph completion[J]. arXiv preprint, 2020,arXiv:2009.14653.
[37]	XU C , NAYYERI M , ALKHOURY F ,et al. Temporal knowledge graph completion based on time series gaussian embedding[C]// Proceedings of the 19th International Semantic Web Conference (ISWC).[S.l.:s.n.], 2020.
[38]	HAN Z , CHEN P , MA Y P ,et al. DyERNIE:dynamic evolution of Riemannian manifold embeddings for temporal knowledge graph completion[C]// Proceedings of 2020 the Conference on Empirical Methods in Natural Language Processing (EMNLP).[S. l]:Association for Computational Linguistics, 2020: 7301-7316.
[39]	GUTIéRREZ-BASULTO V , SCHOCKAERT S . From knowledge graph embedding to ontology embedding? An analysis of the compatibility between vector space representations and rules[C]// Proceedings of the 16th International Conference on the Principles of Knowledge Representation and Reasoning (KR).[S.l.:s.n.], 2018: 379-388.
[40]	FATEMI B , RAVANBAKHSH S , POOLE D . Improved knowledge graph embedding using background taxonomic information[C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI). Palo Alto:AAAI Press, 2019: 3526-3533.
[41]	DU J F , QI K X , WAN H ,et al. Enhancing knowledge graph embedding from a logical perspective[C]// Proceedings of the 7th Joint International Semantic Technology Conference (JIST).[S.l.:s.n.], 2017: 232-247.
[42]	DU J F , QI K X , SHEN Y M . Knowledge graph embedding with logical consistency[C]// Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data (CCL).[S.l.:s.n.], 2018: 123-135.

数据集	实体数/个	关系数/条	时间跨度	更新时间间隔
GDELT-500	500	20	2015—2016年	15 min
ICEWS14	7 128/6 869	230	2014年	每天
ICEWS05-15	10 094	251	2005—2015年	每天
Wikidata11k	11 134	95	25—2020年	每年
Wikidata12k	12 554	24	1479—2018年	每年
YAGO11k	10 623	10	公元前453—2844年	每年
YAGO15k	15 403	34	1513—2017年	每年

模型		ICEWS14			ICEWS05-15			Wikidata11k
模型	MRR	Hit@1	Hit@10	MRR	Hit@1	Hit@10	MRR	Hit@1	Hit@10
TransE^*	0.280	9.4	63.7	0.294	9.0	66.3	0.316	18.1	65.9
DistMult^*	0.439	32.3	67.2	0.456	33.7	69.1	0.316	18.1	66.1
ConT⁺	0.185	11.7	31.5	0.163	10.5	27.2	-	-	-
TTransE^*	0.255	7.4	60.1	0.271	8.4	61.6	0.488	33.9	80.6
HyTE⁺	0.297	10.8	65.5	0.316	11.6	68.1	-	-	-
TA-TransE^*	0.275	9.5	62.5	0.299	9.6	66.8	0.484	32.9	80.7
TA-DistMult^*	0.477	36.3	68.6	0.474	34.6	72.8	0.700	65.2	78.5
DE-SimplE⁺	0.526	41.8	72.5	0.513	39.2	74.8	0.310	18.4	62.5
TComplEx^#	0.560	47.0	73.0	0.580	49.0	76.0	0.731	67.3	84.5
TNTComplEx^#	0.560	46.0	74.0	0.600	50.0	78.0	0.718	65.4	85.6