{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:40:05Z","timestamp":1740123605233,"version":"3.37.3"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T00:00:00Z","timestamp":1615766400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T00:00:00Z","timestamp":1615766400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["U1509216"],"award-info":[{"award-number":["U1509216"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The National Key Research and Development Program of China","award":["2016YFB1000703"],"award-info":[{"award-number":["2016YFB1000703"]}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"crossref","award":["61472099","61602129"],"award-info":[{"award-number":["61472099","61602129"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1007\/s11227-021-03710-x","type":"journal-article","created":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T10:03:26Z","timestamp":1615802606000},"page":"10959-10983","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["SDLER: stacked dedupe learning for entity resolution in big data era"],"prefix":"10.1007","volume":"77","author":[{"given":"Alladoumbaye","family":"Ngueilbaye","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7521-2871","authenticated-orcid":false,"given":"Hongzhi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daouda Ahmat","family":"Mahamat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7154-2307","authenticated-orcid":false,"given":"Ibrahim A.","family":"Elgendy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,15]]},"reference":[{"key":"3710_CR1","doi-asserted-by":"publisher","first-page":"104857","DOI":"10.1016\/j.compag.2019.104857","volume":"163","author":"VCF Aiken","year":"2019","unstructured":"Aiken VCF, Dorea JRR, Acedo JS, de Sousa FG, Dias FG, de Magalhaes Rosa GJ (2019) Record linkage for farm-level data analytics: comparison of deterministic, stochastic and machine learning methods. Comput Elect Agric 163:104857","journal-title":"Comput Elect Agric"},{"key":"3710_CR2","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.datak.2018.07.005","volume":"117","author":"A Allam","year":"2018","unstructured":"Allam A, Skiadopoulos S, Kalnis P (2018) Improved suffix blocking for record linkage and entity resolution. Data Knowl Engin 117:98\u2013113","journal-title":"Data Knowl Engin"},{"issue":"4","key":"3710_CR3","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1007\/s10619-013-7129-3","volume":"31","author":"N Ayat","year":"2013","unstructured":"Ayat N, Akbarinia R, Afsarmanesh H, Valduriez P (2013) Entity resolution for distributed probabilistic data. Distrib Parallel Databases 31(4):509\u2013542","journal-title":"Distrib Parallel Databases"},{"key":"3710_CR4","unstructured":"Berglund M, Raiko T, Honkala M, K\u00e4rkk\u00e4inen L, Vetek A, Karhunen JT (2015) Bidirectional recurrent neural networks as generative models. In: Advances in neural information processing systems, pp 856\u2013864"},{"key":"3710_CR5","unstructured":"Binette O, Steorts RC (2020) (almost) all of entity resolution, arXiv preprint arXiv:2008.04443"},{"key":"3710_CR6","first-page":"135","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski P, Grave E, Joulin A, Mikolov T (2017) Enriching word vectors with subword information, transactions of the association for. Comput Linguist 5:135\u2013146","journal-title":"Comput Linguist"},{"issue":"3","key":"3710_CR7","first-page":"1","volume":"12","author":"Z Chen","year":"2018","unstructured":"Chen Z, Liu B (2018) Lifelong machine learning, synthesis lectures on artificial intelligence and machine. Learning 12(3):1\u2013207","journal-title":"Learning"},{"key":"3710_CR8","volume-title":"Deep learning mit python und keras: das praxis-handbuch vom entwickler der keras-bibliothek","author":"F Chollet","year":"2018","unstructured":"Chollet F (2018) Deep learning mit python und keras: das praxis-handbuch vom entwickler der keras-bibliothek. MITP-Verlags GmbH & Co. KG, Germany"},{"issue":"9","key":"3710_CR9","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1109\/TKDE.2011.127","volume":"24","author":"P Christen","year":"2011","unstructured":"Christen P (2011) A survey of indexing techniques for scalable record linkage and deduplication. IEEE Trans Knowl Data Eng 24(9):1537\u20131555","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"3710_CR10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31164-2","volume-title":"Data matching: concepts and techniques for record linkage, entity resolution, and duplicate detection","author":"P Christen","year":"2012","unstructured":"Christen P (2012) Data matching: concepts and techniques for record linkage, entity resolution, and duplicate detection. Springer, Berlin"},{"key":"3710_CR11","unstructured":"Christophides V, Efthymiou V, Palpanas T, Papadakis G, Stefanidis K (2019) End-to-end entity resolution for big data: a survey, arXiv preprint arXiv:1905.06397"},{"issue":"6","key":"3710_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3418896","volume":"53","author":"V Christophides","year":"2020","unstructured":"Christophides V, Efthymiou V, Palpanas T, Papadakis G, Stefanidis K (2020) An overview of end-to-end entity resolution for big data. ACM Comput Surv (CSUR) 53(6):1\u201342","journal-title":"ACM Comput Surv (CSUR)"},{"key":"3710_CR13","doi-asserted-by":"crossref","unstructured":"Doan A, Ardalan A, Ballard J, Das S, Govind Y, Konda P, Li H, Mudgal S, Paulson E, Suganthan GP et al (2017) Human-in-the-loop challenges for entity matching: a midterm report. In: Proceedings of the 2nd workshop on human-in-the-loop data analytics, pp 1\u20136","DOI":"10.1145\/3077257.3077268"},{"issue":"11","key":"3710_CR14","doi-asserted-by":"publisher","first-page":"1454","DOI":"10.14778\/3236187.3236198","volume":"11","author":"M Ebraheem","year":"2018","unstructured":"Ebraheem M, Thirumuruganathan S, Joty S, Ouzzani M, Tang N (2018) Distributed representations of tuples for entity resolution. Proceed VLDB Endowment 11(11):1454\u20131467","journal-title":"Proceed VLDB Endowment"},{"key":"3710_CR15","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.eswa.2017.03.010","volume":"80","author":"JG Enr\u00edquez","year":"2017","unstructured":"Enr\u00edquez JG, Dom\u00ednguez-Mayo F, Escalona M, Ross M, Staples G (2017) Entity reconciliation in big data sources: a systematic mapping study. Exp Syst Appl 80:14\u201327","journal-title":"Exp Syst Appl"},{"issue":"6","key":"3710_CR16","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1007\/s11390-018-1882-8","volume":"33","author":"S-S Gong","year":"2018","unstructured":"Gong S-S, Hu W, Ge W-Y, Qu Y-Z (2018) Modeling topic-based human expertise for crowd entity resolution. J Comput Sci Technol 33(6):1204\u20131218","journal-title":"J Comput Sci Technol"},{"key":"3710_CR17","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press, US"},{"key":"3710_CR18","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.procs.2016.09.306","volume":"95","author":"RD Gottapu","year":"2016","unstructured":"Gottapu RD, Dagli C, Ali B (2016) Entity resolution using convolutional neural network. Proced Comput Sci 95:153\u2013158","journal-title":"Proced Comput Sci"},{"key":"3710_CR19","doi-asserted-by":"crossref","unstructured":"JeffreyPennington R, Manning C (2014) Glove: Global vectors for word representation. In: Conference on Empirical Methods in Natural Language Processing, Citeseer","DOI":"10.3115\/v1\/D14-1162"},{"key":"3710_CR20","doi-asserted-by":"crossref","unstructured":"Jiang L, Meng D, Zhao Q, Shan S, Hauptmann AG (2015) Self-paced curriculum learning. In: Twenty-Ninth AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v29i1.9608"},{"key":"3710_CR21","doi-asserted-by":"crossref","unstructured":"Kooli N, Allesiardo R, Pigneul E (2018) Deep learning based approach for entity resolution in databases. In: Asian Conference on Intelligent Information and Database Systems. Springer, pp 3\u201312","DOI":"10.1007\/978-3-319-75420-8_1"},{"issue":"2","key":"3710_CR22","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.datak.2009.10.003","volume":"69","author":"H K\u00f6pcke","year":"2010","unstructured":"K\u00f6pcke H, Rahm E (2010) Frameworks for entity matching: a comparison. Data Knowl Eng 69(2):197\u2013210","journal-title":"Data Knowl Eng"},{"key":"3710_CR23","doi-asserted-by":"crossref","unstructured":"Li J, Luong M-T, Jurafsky D, Hovy E (2015) When are tree structures necessary for deep learning of representations?. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp 2304\u20132314","DOI":"10.18653\/v1\/D15-1278"},{"key":"3710_CR24","doi-asserted-by":"crossref","unstructured":"Li L (2018) Entity resolution in big data era: challenges and applications. In: International Conference on Database Systems for Advanced Applications. Springer, pp 114\u2013117","DOI":"10.1007\/978-3-319-91455-8_11"},{"issue":"1","key":"3710_CR25","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1109\/TKDE.2014.2320713","volume":"27","author":"L Li","year":"2014","unstructured":"Li L, Li J, Gao H (2014) Rule-based method for entity resolution. IEEE Trans Knowl Data Eng 27(1):250\u2013263","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"5","key":"3710_CR26","doi-asserted-by":"publisher","first-page":"912","DOI":"10.1109\/TKDE.2019.2898191","volume":"32","author":"Y Lin","year":"2019","unstructured":"Lin Y, Wang H, Li J, Gao H (2019) Efficient entity resolution on heterogeneous records. IEEE Trans Knowl Data Eng 32(5):912\u2013926","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"3710_CR27","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1007\/s11390-017-1731-1","volume":"32","author":"X-L Liu","year":"2017","unstructured":"Liu X-L, Wang H-Z, Li J-Z, Gao H (2017) Entitymanager: managing dirty data based on entity resolution. J Comput Sci Technol 32(3):644\u2013662","journal-title":"J Comput Sci Technol"},{"key":"3710_CR28","doi-asserted-by":"publisher","first-page":"e258","DOI":"10.7717\/peerj-cs.258","volume":"6","author":"A Maratea","year":"2020","unstructured":"Maratea A, Ciaramella A, Cianci GP (2020) Record linkage of banks and municipalities through multiple criteria and neural networks. PeerJ Comput Sci 6:e258","journal-title":"PeerJ Comput Sci"},{"key":"3710_CR29","unstructured":"Mihalcea R (2004) Co-training and self-training for word sense disambiguation. In: Proceedings of the Eighth Conference on Computational Natural Language Learning (CoNLL-2004) at HLT-NAACL 2004, pp 33\u201340"},{"key":"3710_CR30","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. arXiv preprint https:\/\/arxiv.org\/abs\/1310.4546"},{"key":"3710_CR31","doi-asserted-by":"crossref","unstructured":"Mitash C, Bekris KE, Boularias A (2017) A self-supervised learning system for object detection using physics simulation and multi-view pose estimation. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp 545\u2013551","DOI":"10.1109\/IROS.2017.8202206"},{"key":"3710_CR32","doi-asserted-by":"publisher","unstructured":"Ngueilbaye A, Wang H, Mahamat DA, Junaidu SB (2021) Modulo 9 model-based learning for missing data imputation. Appl Soft Comput 103:107167. https:\/\/doi.org\/10.1016\/j.asoc.2021.107167","DOI":"10.1016\/j.asoc.2021.107167"},{"key":"3710_CR33","doi-asserted-by":"crossref","unstructured":"Mudgal S, Li H, Rekatsinas T, Doan A, Park Y, Krishnan G, Deep R, Arcaute E, Raghavendra V (2018) Deep learning for entity matching: a design space exploration. In: Proceedings of the 2018 International Conference on Management of Data, pp 19\u201334","DOI":"10.1145\/3183713.3196926"},{"issue":"5","key":"3710_CR34","first-page":"1564","volume":"5","author":"A Ngueilbaye","year":"2016","unstructured":"Ngueilbaye A, Lei L, Wang H (2016) Comparative study of data mining techniques on heart disease prediction system: a case study for the \u201crepublic of chad.\u201d Int J Sci Res 5(5):1564\u20131571","journal-title":"Int J Sci Res"},{"key":"3710_CR35","doi-asserted-by":"crossref","unstructured":"Ngueilbaye A, Wang H, Khan M, Mahamat DA (2021) Adoption of human metabolic processes as Data Quality Based Models. J Supercomput 77:1779\u20131817","DOI":"10.1007\/s11227-020-03300-3"},{"issue":"2","key":"3710_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3377455","volume":"53","author":"G Papadakis","year":"2020","unstructured":"Papadakis G, Skoutas D, Thanos E, Palpanas T (2020) Blocking and filtering techniques for entity resolution: a survey. ACM Comput Surv (CSUR) 53(2):1\u201342","journal-title":"ACM Comput Surv (CSUR)"},{"key":"3710_CR37","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-3096-1","volume-title":"Pro deep learning with tensor flow","author":"S Pattanayak","year":"2017","unstructured":"Pattanayak S, Pattanayak, John S (2017) Pro deep learning with tensor flow. Springer, Berlin"},{"key":"3710_CR38","volume-title":"Learning over dirty data without cleaning","author":"J Picado","year":"2020","unstructured":"Picado J, Davis J, Termehchy A, Lee GY (2020) Learning over dirty data without cleaning. Association for computing machinery, New York"},{"key":"3710_CR39","doi-asserted-by":"crossref","unstructured":"Qian K, Popa L, Sen P (2017) Active learning for large-scale entity resolution. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp 1379\u20131388","DOI":"10.1145\/3132847.3132949"},{"key":"3710_CR40","doi-asserted-by":"crossref","unstructured":"Ratner AJ, Bach SH, Ehrenberg HR, R\u00e9 C (2017) Snorkel: Fast training set generation for information extraction. In: Proceedings of the 2017 ACM International Conference on Management of Data, pp 1683\u20131686","DOI":"10.1145\/3035918.3056442"},{"key":"3710_CR41","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.datak.2017.10.004","volume":"112","author":"OF Reyes-Galaviz","year":"2017","unstructured":"Reyes-Galaviz OF, Pedrycz W, He Z, Pizzi NJ (2017) A supervised gradient-based learning algorithm for optimized entity resolution. Data Knowl Eng 112:106\u2013129","journal-title":"Data Knowl Eng"},{"issue":"2","key":"3710_CR42","doi-asserted-by":"publisher","first-page":"189","DOI":"10.14778\/3149193.3149199","volume":"11","author":"R Singh","year":"2017","unstructured":"Singh R, Meduri VV, Elmagarmid A, Madden S, Papotti P, Quian\u00e9-Ruiz J-A, Solar-Lezama A, Tang N (2017) Synthesizing entity matching rules by examples. Proceed VLDB Endow 11(2):189\u2013202","journal-title":"Proceed VLDB Endow"},{"issue":"10","key":"3710_CR43","doi-asserted-by":"publisher","first-page":"1843","DOI":"10.3724\/SP.J.1016.2011.01843","volume":"34","author":"H-Z Wang","year":"2011","unstructured":"Wang H-Z, Fan W-F (2011) Object identification on complex data: a survey. Jisuanji Xuebao Chin J Comput 34(10):1843\u20131852","journal-title":"Jisuanji Xuebao Chin J Comput"},{"key":"3710_CR44","doi-asserted-by":"crossref","unstructured":"Wang H, Zhang X, Li J, Gao H (2013) Productseeker: entity-based product retrieval for e-commerce. In: Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp 1085\u20131086","DOI":"10.1145\/2484028.2484205"},{"issue":"1","key":"3710_CR45","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/JPROC.2015.2487976","volume":"104","author":"J Wang","year":"2015","unstructured":"Wang J, Liu W, Kumar S, Chang S-F (2015) Learning to hash for indexing big data-a survey. Proceed IEEE 104(1):34\u201357","journal-title":"Proceed IEEE"},{"key":"3710_CR46","unstructured":"Wang J, Shen HT, Song J, Ji J (2014) Hashing for similarity search: a survey, arXiv preprint arXiv:1408.2927"},{"key":"3710_CR47","unstructured":"Yalavarthi VK, Ke X, Khan A (2017) Probabilistic entity resolution with imperfect crowd. CoRR"},{"key":"3710_CR48","volume-title":"Automatic speech recognition","author":"D Yu","year":"2016","unstructured":"Yu D, Deng L (2016) Automatic speech recognition. Springer, Berlin"},{"issue":"2","key":"3710_CR49","doi-asserted-by":"publisher","first-page":"366","DOI":"10.1007\/s11390-018-1824-5","volume":"33","author":"A-Z Zhang","year":"2018","unstructured":"Zhang A-Z, Li J-Z, Gao H, Chen Y-B, Ma H-Z, Bah MJ (2018) Crowdola: online aggregation on duplicate data powered by crowdsourcing. J Comput Sci Technol 33(2):366\u2013379","journal-title":"J Comput Sci Technol"},{"key":"3710_CR50","unstructured":"Zhang J, Wu X, Way A, Liu Q (2017) Fast gated neural domain adaptation: Language model as a case study, Association for Computational Linguistics"},{"key":"3710_CR51","doi-asserted-by":"crossref","unstructured":"Zhang W, Wei H, Sisman B, Dong XL, Faloutsos C, Page D (2020) Autoblock: a hands-off blocking framework for entity matching. In: Proceedings of the 13th International Conference on Web Search and Data Mining, pp 744\u2013752","DOI":"10.1145\/3336191.3371813"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-021-03710-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-021-03710-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-021-03710-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,21]],"date-time":"2022-12-21T14:09:51Z","timestamp":1671631791000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-021-03710-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,15]]},"references-count":51,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["3710"],"URL":"https:\/\/doi.org\/10.1007\/s11227-021-03710-x","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2021,3,15]]},"assertion":[{"value":"23 February 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 March 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}