{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:57:28Z","timestamp":1740171448738,"version":"3.37.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2021,7,6]],"date-time":"2021-07-06T00:00:00Z","timestamp":1625529600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,7,6]],"date-time":"2021-07-06T00:00:00Z","timestamp":1625529600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100006162","name":"Funda\u00e7\u00e3o de Amparo \u00e0 Ci\u00eancia e Tecnologia do Estado de Pernambuco","doi-asserted-by":"publisher","award":["IBPG-1172-1.03\/16"],"award-info":[{"award-number":["IBPG-1172-1.03\/16"]}],"id":[{"id":"10.13039\/501100006162","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Data Semant"],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1007\/s13740-021-00134-x","type":"journal-article","created":{"date-parts":[[2021,7,6]],"date-time":"2021-07-06T05:02:32Z","timestamp":1625547752000},"page":"309-325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DeepEx: A Robust Weak Supervision System for Knowledge Base Augmentation"],"prefix":"10.1007","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4705-9766","authenticated-orcid":false,"given":"Johny","family":"Moreira","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luciano","family":"Barbosa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,7,6]]},"reference":[{"key":"134_CR1","first-page":"4","volume":"1","author":"B Baharudin","year":"2010","unstructured":"Baharudin B, Lee LH, Khan K (2010) A review of machine learning algorithms for text-documents classification. J Adv Inf Technol 1:4\u201320","journal-title":"J Adv Inf Technol"},{"key":"134_CR2","volume-title":"Entity-oriented search. the information retrieval series","author":"K Balog","year":"2018","unstructured":"Balog K (2018) Entity-oriented search. the information retrieval series. Springer International Publishing, New York"},{"key":"134_CR3","doi-asserted-by":"crossref","unstructured":"Banerjee S, Tsioutsiouliklis K (2018) Relation extraction using multi-encoder lstm network on a distant supervised dataset. In: IEEE 12th International Conference on Semantic Computing","DOI":"10.1109\/ICSC.2018.00040"},{"key":"134_CR4","doi-asserted-by":"crossref","unstructured":"Bollacker K, Evans C, Paritosh P, Sturge T, Taylor J (2008) Freebase: A collaboratively created graph database for structuring human knowledge. Proceedings of the International Conference on Management of Data","DOI":"10.1145\/1376616.1376746"},{"key":"134_CR5","doi-asserted-by":"publisher","first-page":"1190","DOI":"10.1137\/0916069","volume":"16","author":"RH Byrd","year":"1995","unstructured":"Byrd RH, Lu P, Nocedal J, Zhu C (1995) A limited memory algorithm for bound constrained optimization. SIAM J Sci Comput 16:1190","journal-title":"SIAM J Sci Comput"},{"issue":"3","key":"134_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang CC, Lin CJ (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1\u201327","journal-title":"ACM Trans Intell Syst Technol"},{"key":"134_CR7","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1162\/tacl_a_00104","volume":"4","author":"JP Chiu","year":"2016","unstructured":"Chiu JP, Nichols E (2016) Named entity recognition with bidirectional LSTM-CNNs. Trans Assoc Comput Linguist 4:357\u2013370","journal-title":"Trans Assoc Comput Linguist"},{"key":"134_CR8","unstructured":"Cohen WW, Ravikumar P, Fienberg SE, et\u00a0al. (2003) A comparison of string distance metrics for name-matching tasks. In: Proceedings of the International Conference on Information Integration on the Web, p 73\u201378"},{"key":"134_CR9","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273\u2013293","journal-title":"Mach Learn"},{"key":"134_CR10","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), Association for Computational Linguistics"},{"key":"134_CR11","doi-asserted-by":"crossref","unstructured":"Dong X, Gabrilovich E, Heitz G, Horn W, Lao N, Murphy K, Strohmann T, Sun S, Zhang W (2014) Knowledge vault: a web-scale approach to probabilistic knowledge fusion. Proceedings of the 20th International Conference on Knowledge Discovery and Data Mining pp 601\u2013610","DOI":"10.1145\/2623330.2623623"},{"key":"134_CR12","unstructured":"Dozat T (2016) Incorporating nesterov momentum into adam. International Conference on Learning Representations Workshop"},{"key":"134_CR13","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1609\/aimag.v31i3.2303","volume":"31","author":"D Ferrucci","year":"2010","unstructured":"Ferrucci D, Brown E, Chu-Carroll J, Fan J, Gondek D, Kalyanpur AA, Lally A, Murdock JW, Nyberg E, Prager J, Schlaefer N, Welty C (2010) Building watson: an overview of the DeepQA project. AI Magazine 31:59\u201379","journal-title":"AI Magazine"},{"key":"134_CR14","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","volume":"18","author":"A Graves","year":"2005","unstructured":"Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw 18:602\u2013610","journal-title":"Neural Netw"},{"key":"134_CR15","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MIS.2009.36","volume":"24","author":"A Halevy","year":"2009","unstructured":"Halevy A, Norvig P, Pereira F (2009) The unreasonable effectiveness of data. IEEE Intell Syst 24:8\u201312","journal-title":"IEEE Intell Syst"},{"key":"134_CR16","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.ijresmar.2018.09.009","volume":"36","author":"J Hartmann","year":"2019","unstructured":"Hartmann J, Huppertz J, Schamp C, Heitmann M (2019) Comparing automated text classification methods. Int J Res Market 36:20\u201338","journal-title":"Int J Res Market"},{"key":"134_CR17","doi-asserted-by":"crossref","unstructured":"Kim Y (2014) Convolutional neural networks for sentence classification. In: Proceeding of the Conference on Empirical Methods in Natural Language Processing","DOI":"10.3115\/v1\/D14-1181"},{"key":"134_CR18","unstructured":"Lafferty JD, McCallum A, Pereira FCN (2001) Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: Proceeding of the 18th International Conference on Machine Learning"},{"key":"134_CR19","doi-asserted-by":"crossref","unstructured":"Lange D, B\u00f6hm C, Naumann F (2010) Extracting structured information from wikipedia articles to populate infoboxes. In: Proceeding of the 19th ACM International Conference on Information and Knowledge Management","DOI":"10.1145\/1871437.1871698"},{"issue":"2","key":"134_CR20","doi-asserted-by":"publisher","first-page":"167","DOI":"10.3233\/SW-140134","volume":"6","author":"J Lehmann","year":"2015","unstructured":"Lehmann J, Isele R, Jakob M, Jentzsch A, Kontokostas D, Mendes PN, Hellmann S, Morsey M, Van Kleef P, Auer S et al (2015) Dbpedia-a large-scale, multilingual knowledge base extracted from wikipedia. Semantic Web 6(2):167\u2013195","journal-title":"Semantic Web"},{"key":"134_CR21","doi-asserted-by":"crossref","unstructured":"Lockard C, Dong XL, Einolghozati A, Shiralkar P (2018) Ceres: Distantly supervised relation extraction from the semi-structured web. Proceeding VLDB Endowment","DOI":"10.14778\/3231751.3231758"},{"key":"134_CR22","doi-asserted-by":"crossref","unstructured":"Lockard C, Shiralkar P, Dong XL, Hajishirzi H (2020) ZeroShotCeres: Zero-shot relation extraction from semi-structured webpages. In: Proceeding of the 58th Annual Meeting of the Association for Computational Linguistics","DOI":"10.18653\/v1\/2020.acl-main.721"},{"key":"134_CR23","doi-asserted-by":"crossref","unstructured":"Martinez-Rodriguez JL, Hogan A, Lopez-Arevalo I (2020) Information Extraction meets the Semantic Web: A Survey, vol\u00a011","DOI":"10.3233\/SW-180333"},{"key":"134_CR24","unstructured":"Min B, Grishman R, Wan L, Wang C, Gondek D (2013) Distant supervision for relation extraction with an incomplete knowledge base. Proceeding of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"key":"134_CR25","doi-asserted-by":"crossref","unstructured":"Mintz M, Bills S, Snow R, Jurafsky D (2009) Distant supervision for relation extraction without labeled data. In: Proceeding of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing, vol\u00a02","DOI":"10.3115\/1690219.1690287"},{"key":"134_CR26","doi-asserted-by":"crossref","unstructured":"Nickel M, Tresp V, Kriegel HP (2012) Factorizing yago: Scalable machine learning for linked data. In: Proceeding of the 21st International Conference on World Wide Web","DOI":"10.1145\/2187836.2187874"},{"key":"134_CR27","doi-asserted-by":"crossref","first-page":"12","DOI":"10.3233\/SW-160218","volume":"8","author":"H Paulheim","year":"2016","unstructured":"Paulheim H (2016) Knowledge graph refinement: a survey of approaches and evaluation methods. Semant Web 8:12","journal-title":"Semant Web"},{"key":"134_CR28","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/978-3-319-58068-5_25","volume":"81","author":"H Paulheim","year":"2017","unstructured":"Paulheim H (2017) Data-driven joint debugging of the dbpedia mappings and ontology. Semant Web 81:404\u2013418","journal-title":"Semant Web"},{"key":"134_CR29","volume-title":"Type inference on noisy rdf data. in the semantic web","author":"H Paulheim","year":"2013","unstructured":"Paulheim H, Bizer C (2013) Type inference on noisy rdf data. in the semantic web. Springer, Berlin"},{"key":"134_CR30","doi-asserted-by":"publisher","first-page":"63","DOI":"10.4018\/ijswis.2014040104","volume":"10","author":"H Paulheim","year":"2014","unstructured":"Paulheim H, Bizer C (2014) Improving the quality of linked data using statistical distributions. Int J Semant Web Inf Syst 10:63\u201386","journal-title":"Int J Semant Web Inf Syst"},{"key":"134_CR31","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C (2014) Glove: Global Vectors for Word Representation. In: Proceeding of the Conference on Empirical Methods in Natural Language Processing","DOI":"10.3115\/v1\/D14-1162"},{"key":"134_CR32","doi-asserted-by":"crossref","unstructured":"Peters M, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L (2018) Deep contextualized word representations. In: Proceeding of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), Association for Computational Linguistics","DOI":"10.18653\/v1\/N18-1202"},{"key":"134_CR33","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.neunet.2018.01.006","volume":"100","author":"J Qu","year":"2018","unstructured":"Qu J, Ouyang D, Hua W, Ye Y, Li X (2018) Distant supervision for neural relation extraction integrated with word attention and property features. Neural Netw 100:59\u201369","journal-title":"Neural Netw"},{"key":"134_CR34","unstructured":"Radford A, Narasimhan K, Salimans T, Sutskever I (2018) Improving language understanding by generative pre-training"},{"key":"134_CR35","unstructured":"Ratner A, Sa CD, Wu S, Selsam D, R\u00e9 C (2016) Data programming: Creating large training sets, quickly. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, p 3574\u20133582"},{"issue":"2","key":"134_CR36","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/s00778-019-00552-1","volume":"29","author":"A Ratner","year":"2020","unstructured":"Ratner A, Bach SH, Ehrenberg H, Fries J, Wu S, R\u00e9 C (2020) Snorkel: rapid training data creation with weak supervision. VLDB J 29(2):709\u2013730","journal-title":"VLDB J"},{"key":"134_CR37","doi-asserted-by":"publisher","first-page":"100546","DOI":"10.1016\/j.websem.2019.100546","volume":"600","author":"P Ristoski","year":"2020","unstructured":"Ristoski P, Gentile AL, Alba A, Gruhl D, Welch S (2020) Large-scale relation extraction from web documents and knowledge graphs with human-in-the-loop. J Web Semant 600:100546","journal-title":"J Web Semant"},{"key":"134_CR38","doi-asserted-by":"crossref","unstructured":"S\u00e1ez T, Hogan A (2018) Automatically generating wikipedia info-boxes from wikidata. In: Companion Proceeding of the The Web Conference 2018, WWW \u201918, p 1823\u20131830","DOI":"10.1145\/3184558.3191647"},{"key":"134_CR39","doi-asserted-by":"crossref","unstructured":"Sleeman J, Finin T (2013) Type prediction for efficient coreference resolution in heterogeneous semantic graphs. Proceeding of the IEEE 7th International Conferenec on Semantic Computing","DOI":"10.1109\/ICSC.2013.22"},{"key":"134_CR40","unstructured":"Sleeman J, Finin T, Joshi A (2015) Topic modeling for RDF graphs. CEUR Workshop Proceeding"},{"issue":"1","key":"134_CR41","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"134_CR42","doi-asserted-by":"crossref","unstructured":"Suchanek FM, Kasneci G, Weikum G (2007) Yago: a core of semantic knowledge. Proceeding of the 16th International Conference on World Wide Web p 697\u2013706","DOI":"10.1145\/1242572.1242667"},{"key":"134_CR43","unstructured":"Takamatsu S, Sato I, Nakagawa H (2012) Reducing wrong labels in distant supervision for relation extraction. In: Proceeding of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers, pp 721\u2013729"},{"key":"134_CR44","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser u, Polosukhin I (2017) Attention is all you need. In: Proceeding of the 31st International Conference on Neural Information Processing Systems, p 6000\u20136010"},{"issue":"10","key":"134_CR45","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1145\/2629489","volume":"57","author":"D Vrande\u010di\u0107","year":"2014","unstructured":"Vrande\u010di\u0107 D, Kr\u00f6tzsch M (2014) Wikidata: a free collaborative knowledgebase. Commun ACM 57(10):78\u201385","journal-title":"Commun ACM"},{"key":"134_CR46","doi-asserted-by":"crossref","unstructured":"Wallace E, Wang Y, Li S, Singh S, Gardner M (2019) Do NLP models know numbers? probing numeracy in embeddings. In: Proceeding of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pp 5307\u20135315","DOI":"10.18653\/v1\/D19-1534"},{"key":"134_CR47","first-page":"192","volume":"55","author":"F Wilcoxon","year":"1945","unstructured":"Wilcoxon F (1945) Individual comparisons by ranking methods. Biom Bull 55:192","journal-title":"Biom Bull"},{"key":"134_CR48","doi-asserted-by":"crossref","unstructured":"Wu F, Weld DS (2007) Autonomously semantifying wikipedia. In: Proceeding of the 16th ACM Conference on Information and Knowledge Management, pp 41\u201350","DOI":"10.1145\/1321440.1321449"},{"issue":"3","key":"134_CR49","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/MCI.2018.2840738","volume":"13","author":"T Young","year":"2018","unstructured":"Young T, Hazarika D, Poria S, Cambria E (2018) Recent trends in deep learning based natural language processing [Review Article]. IEEE Comput Intell Mag 13(3):55\u201375","journal-title":"IEEE Comput Intell Mag"},{"key":"134_CR50","unstructured":"Yus R, Mulwad V, Finin T, Mena E, et\u00a0al. (2014) Infoboxer: using statistical and semantic knowledge to help create wikipedia infoboxes. In: 13th International Semantic Web Conference"}],"container-title":["Journal on Data Semantics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13740-021-00134-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13740-021-00134-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13740-021-00134-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T23:16:31Z","timestamp":1672701391000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13740-021-00134-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,6]]},"references-count":50,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2021,12]]}},"alternative-id":["134"],"URL":"https:\/\/doi.org\/10.1007\/s13740-021-00134-x","relation":{},"ISSN":["1861-2032","1861-2040"],"issn-type":[{"type":"print","value":"1861-2032"},{"type":"electronic","value":"1861-2040"}],"subject":[],"published":{"date-parts":[[2021,7,6]]},"assertion":[{"value":"12 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 April 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The datasets used in this paper are publicly available on.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Data Availability"}},{"value":"The source code of our solution is publicly available on.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Code Availability"}}]}}