{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T14:16:22Z","timestamp":1753884982011,"version":"3.41.2"},"reference-count":42,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,4,16]],"date-time":"2021-04-16T00:00:00Z","timestamp":1618531200000},"content-version":"vor","delay-in-days":105,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906159"],"award-info":[{"award-number":["61906159"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JBK2003008"],"award-info":[{"award-number":["JBK2003008"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Complexity"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Knowledge graphs (KGs) entity typing aims to predict the potential types to an entity, that is, (<jats:italic>entity, entity type<\/jats:italic>\u2009<jats:italic>=<\/jats:italic>\u2009<jats:italic>?<\/jats:italic>). Recently, several embedding models are proposed for KG entity types prediction according to the existing typing information of the (<jats:italic>entity, entity type<\/jats:italic>) tuples in KGs. However, most of them unreasonably assume that all existing entity typing instances in KGs are completely correct, which ignore the nonnegligible entity type noises and may lead to potential errors for the downstream tasks. To address this problem, we propose <jats:bold>ConfE<\/jats:bold>, a novel confidence\u2010aware embedding approach for modeling the (<jats:italic>entity, entity type<\/jats:italic>) tuples, which takes <jats:italic>tuple confidence<\/jats:italic> into consideration for learning better embeddings. Specifically, we learn the embeddings of entities and entity types in separate entity space and entity type space since they are different objects in KGs. We utilize an asymmetric matrix to specify the interaction of their embeddings and incorporate the <jats:italic>tuple confidence<\/jats:italic> as well. To make the <jats:italic>tuple confidence<\/jats:italic> more universal, we consider only the internal structural information in existing KGs. We evaluate our model on two tasks, including entity type noise detection and entity type prediction. The extensive experimental results in two public benchmark datasets (i.e., FB15kET and YAGO43kET) demonstrate that our proposed model outperforms all baselines on all tasks, which verify the effectiveness of ConfE in learning better embeddings on noisy KGs. The source code and data of this work can be obtained from <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/swufenlp\/ConfE\">https:\/\/github.com\/swufenlp\/ConfE<\/jats:ext-link>.<\/jats:p>","DOI":"10.1155\/2021\/3473849","type":"journal-article","created":{"date-parts":[[2021,4,17]],"date-time":"2021-04-17T00:05:32Z","timestamp":1618617932000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Confidence\u2010Aware Embedding for Knowledge Graph Entity Typing"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8454-0025","authenticated-orcid":false,"given":"Yu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayue","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zongjian","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2565-6893","authenticated-orcid":false,"given":"Yun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,4,16]]},"reference":[{"unstructured":"ZhaoY. ZhangA. XieR. LiuK. andWangX. Connecting embeddings for knowledge graph entity typing Proceedings of ACL July 2020 Seattle WA USA.","key":"e_1_2_10_1_2"},{"doi-asserted-by":"crossref","unstructured":"GuptaN. SinghS. andRothD. Entity linking via joint encoding of types descriptions and context Proceedings of EMNLP September 2017 Copenhagen Denmark 2681\u20132690.","key":"e_1_2_10_2_2","DOI":"10.18653\/v1\/D17-1284"},{"doi-asserted-by":"crossref","unstructured":"JainP. KumarP. andChakrabartiS. Type-sensitive knowledge base inference without explicit type supervision Proceedings of ACL July 2018 Melbourne Australia.","key":"e_1_2_10_3_2","DOI":"10.18653\/v1\/P18-2013"},{"doi-asserted-by":"crossref","unstructured":"ElsaharH. GravierC. andLaforestF. Zero-shot question generation from knowledge graphs for unseen predicates and entity types Proceedings of NAACL June 2018 New Orleans LA USA 218\u2013228.","key":"e_1_2_10_4_2","DOI":"10.18653\/v1\/N18-1020"},{"doi-asserted-by":"crossref","unstructured":"BollackerK. EvansC. ParitoshP. SturgeT. andTaylorJ. Freebase: a collaboratively created graph database for structuring human knowledge Proceedings of SIGMOD June 2008 Vancouver Canada 1247\u20131250.","key":"e_1_2_10_5_2","DOI":"10.1145\/1376616.1376746"},{"doi-asserted-by":"crossref","unstructured":"SuchanekF. M. KasneciG. andWeikumG. Yago: a core of semantic knowledge Proceedings of WWW June 2007 Prague Czech Republic 697\u2013706.","key":"e_1_2_10_6_2","DOI":"10.1145\/1242572.1242667"},{"doi-asserted-by":"crossref","unstructured":"DongX. GabrilovichE. HeitzG.et al. Knowledge vault: a web-scale approach to probabilistic knowledge fusion Proceedings of SIGKDD August 2014 New York NY USA 601\u2013610.","key":"e_1_2_10_7_2","DOI":"10.1145\/2623330.2623623"},{"doi-asserted-by":"crossref","unstructured":"ZhouB. KhashabiD. TsaiC.-T. andRothD. Zero-shot open entity typing as type-compatible grounding Procedddings of EMNLP October 2018 Brussels Belgium 2065\u20132076.","key":"e_1_2_10_8_2","DOI":"10.18653\/v1\/D18-1231"},{"doi-asserted-by":"crossref","unstructured":"PujaraJ. AugustineE. andGetoorL. Sparsity and noise: where knowledge graph embeddings fall short Proceedings of EMNLP September 2017 Copenhagen Denmark 1751\u20131756.","key":"e_1_2_10_9_2","DOI":"10.18653\/v1\/D17-1184"},{"doi-asserted-by":"crossref","unstructured":"NeelakantanA.andChangM.-W. Inferring missing entity type instances for knowledge base completion: new dataset and methods 2015 http:\/\/arxiv.org\/abs\/1504.06658.","key":"e_1_2_10_10_2","DOI":"10.3115\/v1\/N15-1054"},{"doi-asserted-by":"crossref","unstructured":"MoonC. JonesP. andSamatovaN. F. Learning entity type embeddings for knowledge graph completion Proceedings of CIKM November 2017 Singapore 2215\u20132218.","key":"e_1_2_10_11_2","DOI":"10.1145\/3132847.3133095"},{"doi-asserted-by":"crossref","unstructured":"ZhangR. KongF. WangC. andMaoY. Embedding of hierarchically typed knowledge bases Proceddings of AAAI February 2018 New Orleans LA USA.","key":"e_1_2_10_12_2","DOI":"10.1609\/aaai.v32i1.11548"},{"doi-asserted-by":"publisher","key":"e_1_2_10_13_2","DOI":"10.3233\/SW-160218"},{"doi-asserted-by":"publisher","key":"e_1_2_10_14_2","DOI":"10.3233\/SW-150175"},{"doi-asserted-by":"crossref","unstructured":"JiangS. LowdD. andDouD. Learning to refine an automatically extracted knowledge base using markov logic Proceeding of ICDM December 2012 Brussels Belgium 912\u2013917.","key":"e_1_2_10_15_2","DOI":"10.1109\/ICDM.2012.156"},{"doi-asserted-by":"crossref","unstructured":"HeindorfS. PotthastM. SteinB. andEngelsG. Vandalism detection in wikidata Proceedings of the International on Conference on Information and Knowledge Management (CIKM\u201916) ACM October 2016 Indianapolis IN USA 327\u2013336.","key":"e_1_2_10_16_2","DOI":"10.1145\/2983323.2983740"},{"doi-asserted-by":"crossref","unstructured":"MeloA.andPaulheimH. Detection of relation assertion errors in knowledge graphs Proceedings of ACM November 2017 Singapore.","key":"e_1_2_10_17_2","DOI":"10.1145\/3148011.3148033"},{"unstructured":"NeilD. BriodyJ. LacosteA. SimA. CreedP. andSaffariA. Interpretable graph convolutional neural networks for inference on noisy knowledge graphs Proceedings of NeurIPS December 2017 Long Beach CA USA.","key":"e_1_2_10_18_2"},{"doi-asserted-by":"crossref","unstructured":"LiangJ. XiaoY. ZhangY. won HwangS. andWangH. Graph-based wrong isa relation detection in a large-scale lexical taxonomy Proceedings of AAAI February 2017 San Francisco CA USA 1178\u20131184.","key":"e_1_2_10_19_2","DOI":"10.1609\/aaai.v31i1.10676"},{"doi-asserted-by":"crossref","unstructured":"XieR. LiuZ. LinF. andLinL. Does william shakespeare really write hamlet? knowledge representation learning with confidence Proceedding of AAAI February 2018 Palo Alto CA USA.","key":"e_1_2_10_20_2","DOI":"10.1609\/aaai.v32i1.11924"},{"doi-asserted-by":"publisher","key":"e_1_2_10_21_2","DOI":"10.3390\/e21111083"},{"doi-asserted-by":"publisher","key":"e_1_2_10_22_2","DOI":"10.4018\/ijswis.2014040104"},{"doi-asserted-by":"publisher","key":"e_1_2_10_23_2","DOI":"10.1007\/978-3-662-45495-4_3"},{"doi-asserted-by":"publisher","key":"e_1_2_10_24_2","DOI":"10.1007\/978-3-642-41335-3_32"},{"doi-asserted-by":"crossref","unstructured":"RenX. HeW. QuM. VossC. R. JiH. andHanJ. Label noise reduction in entity typing by heterogeneous partial-label embedding Proceedings of SIGKDD August 2016 San Francisco CA USA ACM 1825\u20131834.","key":"e_1_2_10_25_2","DOI":"10.1145\/2939672.2939822"},{"doi-asserted-by":"crossref","unstructured":"TempelmeierN. DemidovaE. andDietzeS. Inferring missing categorical information in noisy and sparse web markup Proceedings of WWW April 2018 Lyon France 1297\u20131306.","key":"e_1_2_10_26_2","DOI":"10.1145\/3178876.3186028"},{"doi-asserted-by":"publisher","key":"e_1_2_10_27_2","DOI":"10.1109\/tkde.2017.2754499"},{"doi-asserted-by":"crossref","unstructured":"BordesA. WestonJ. CollobertR. andBengioY. Learning structured embeddings of knowledge bases Proceedings of AAAI August 2011 San Francisco CA USA 301\u2013306.","key":"e_1_2_10_28_2","DOI":"10.1609\/aaai.v25i1.7917"},{"unstructured":"SocherR. ChenD. ManningC. D. andNgA. Y. Reasoning with neural tensor networks for knowledge base completion Proceedings of NeurIPS December 2013 Lake Tahoe NV USA 926\u2013934.","key":"e_1_2_10_29_2"},{"unstructured":"BordesA. UsunierN. Garcia-DuranA. WestonJ. andYakhnenkoO. Translating embeddings for modeling multi-relational data Proceedings of NeurIPS December 2013 Lake Tahoe NV USA 2787\u20132795.","key":"e_1_2_10_30_2"},{"doi-asserted-by":"crossref","unstructured":"WangZ. ZhangJ. FengJ. andChenZ. Knowledge graph embedding by translating on hyperplanes Proceedings of AAAI December 2014 Qu\u00e9bec City Canada 1112\u20131119.","key":"e_1_2_10_31_2","DOI":"10.1609\/aaai.v28i1.8870"},{"doi-asserted-by":"crossref","unstructured":"LinY. LiuZ. SunM. LiuY. andZhuX. Learning entity and relation embeddings for knowledge graph completion Proceedings of AAAI January 2015 Austin TX USA 2181\u20132187.","key":"e_1_2_10_32_2","DOI":"10.1609\/aaai.v29i1.9491"},{"doi-asserted-by":"crossref","unstructured":"XiaoH. HuangM. andZhuX. Transg: a generative model for knowledge graph embedding Proceedings of ACL August 2016 Berlin Germany 2316\u20132325.","key":"e_1_2_10_33_2","DOI":"10.18653\/v1\/P16-1219"},{"unstructured":"TrouillonT. WelblJ. RiedelS. GaussierE. andBouchardG. Complex embeddings for simple link prediction Proceedings of ICML August 2016 New York NY USA 2071\u20132080.","key":"e_1_2_10_34_2"},{"doi-asserted-by":"crossref","unstructured":"XiaoH. HuangM. andZhuX. Ssp: semantic space projection for knowledge graph embedding with text descriptions Proceedings of AAAI February 2017 San Francisco CA USA 3104\u20133110.","key":"e_1_2_10_35_2","DOI":"10.1609\/aaai.v31i1.10952"},{"doi-asserted-by":"crossref","unstructured":"ShiB.andWeningerT. Proje: embedding projection for knowledge graph completion Proceedings of AAAI February 2017 San Francisco CA USA 1236\u20131242.","key":"e_1_2_10_36_2","DOI":"10.1609\/aaai.v31i1.10677"},{"doi-asserted-by":"crossref","unstructured":"DettmersT. PasqualeM. PontusS. andRiedelS. Convolutional 2d knowledge graph embeddings Proceedings of AAAI February 2017 San Francisco CA USA 1811\u20131818.","key":"e_1_2_10_37_2","DOI":"10.1609\/aaai.v32i1.11573"},{"doi-asserted-by":"crossref","unstructured":"NathaniD. ChauhanJ. SharmaC. andKaulM. Learning attention-based embeddings for relation prediction in knowledge graphs Proceedings of ACL July 2019 Florence Italy.","key":"e_1_2_10_38_2","DOI":"10.18653\/v1\/P19-1466"},{"doi-asserted-by":"crossref","unstructured":"NguyenD. Q. VuT. NguyenT. D. NguyenD. Q. andPhungD. A capsule network-based embedding model for knowledge graph completion and search personalization Proceedings of NAACL June 2019 Minneapolis MN USA 2180\u20132189.","key":"e_1_2_10_39_2","DOI":"10.18653\/v1\/N19-1226"},{"doi-asserted-by":"crossref","unstructured":"NguyenD. Q. NguyenT. D. NguyenD. Q. andPhungD. A novel embedding model for knowledge base completion based on convolutional neural network Proceedings of NAACL June 2018 New Orleansm LA USA 327\u2013333.","key":"e_1_2_10_40_2","DOI":"10.18653\/v1\/N18-2053"},{"unstructured":"BordesA. UsunierN. Garcia-DuranA. WestonJ. andYakhnenkoO. A three-way model for collective learning on multi-relational data-28th international conference on machine learning Proceedings of the Joint European Conference on Machine Learning September 2011 Athens Greece 809\u2013816.","key":"e_1_2_10_41_2"},{"doi-asserted-by":"publisher","key":"e_1_2_10_42_2","DOI":"10.1016\/j.knosys.2020.106630"}],"container-title":["Complexity"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2021\/3473849.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/complexity\/2021\/3473849.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/3473849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T22:00:00Z","timestamp":1723240800000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/3473849"}},"subtitle":[],"editor":[{"given":"Daniela","family":"Paolotti","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/3473849"],"URL":"https:\/\/doi.org\/10.1155\/2021\/3473849","archive":["Portico"],"relation":{},"ISSN":["1076-2787","1099-0526"],"issn-type":[{"type":"print","value":"1076-2787"},{"type":"electronic","value":"1099-0526"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2020-07-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-04-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3473849"}}