{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:48:23Z","timestamp":1742914103429,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030757649"},{"type":"electronic","value":"9783030757656"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-75765-6_26","type":"book-chapter","created":{"date-parts":[[2021,5,7]],"date-time":"2021-05-07T09:08:54Z","timestamp":1620378534000},"page":"321-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Active Learning Based Similarity Filtering for Efficient and Effective Record Linkage"],"prefix":"10.1007","author":[{"given":"Charini","family":"Nanayakkara","sequence":"first","affiliation":[]},{"given":"Peter","family":"Christen","sequence":"additional","affiliation":[]},{"given":"Thilina","family":"Ranbaduge","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,5,8]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Arasu, A., G\u00f6tz, M., Kaushik, R.: On active learning of record matching packages. In: ACM SIGMOD. pp. 783\u2013794. Indianapolis (2010)","DOI":"10.1145\/1807167.1807252"},{"key":"26_CR2","doi-asserted-by":"crossref","unstructured":"Bhattacharya, I., Getoor, L.: Collective entity resolution in relational data. ACM TKDD 1(1), 5-es (2007)","DOI":"10.1145\/1217299.1217304"},{"key":"26_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-31164-2","volume-title":"Data Matching - Concepts and Rechniques for Record Linkage, Entity Resolution, and Duplicate Detection","author":"P Christen","year":"2012","unstructured":"Christen, P.: Data Matching - Concepts and Rechniques for Record Linkage, Entity Resolution, and Duplicate Detection. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31164-2"},{"key":"26_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59706-1","volume-title":"Linking Sensitive Data","author":"P Christen","year":"2020","unstructured":"Christen, P., Ranbaduge, T., Schnell, R.: Linking Sensitive Data. Springer, Heidelberg (2020). https:\/\/doi.org\/10.1007\/978-3-030-59706-1"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Dong, X.L., Srivastava, D.: Big Data Integration. Synthesis Lectures on Data Management, Morgan and Claypool Publishers, San Rafael (2015)","DOI":"10.2200\/S00578ED1V01Y201404DTM040"},{"issue":"1","key":"26_CR6","first-page":"1","volume":"12","author":"U Draisbach","year":"2019","unstructured":"Draisbach, U., Christen, P., Naumann, F.: Transforming pairwise duplicates to entity clusters for high-quality duplicate detection. ACM JDIQ 12(1), 1\u201330 (2019)","journal-title":"ACM JDIQ"},{"key":"26_CR7","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.is.2016.12.001","volume":"65","author":"V Efthymiou","year":"2017","unstructured":"Efthymiou, V., Papadakis, G., Papastefanatos, G., Stefanidis, K., Palpanas, T.: Parallel meta-blocking for scaling entity resolution over big heterogeneous data. Inf. Syst. 65, 137\u2013157 (2017)","journal-title":"Inf. Syst."},{"key":"26_CR8","volume-title":"Data Mining: Concepts and Techniques","author":"J Han","year":"2012","unstructured":"Han, J., Kamber, M., Pei, J.: Data Mining: Concepts and Techniques, 3rd edn. Morgan Kaufmann, Burlington (2012)","edition":"3"},{"issue":"3","key":"26_CR9","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1007\/s11222-017-9746-6","volume":"28","author":"D Hand","year":"2017","unstructured":"Hand, D., Christen, P.: A note on using the F-measure for evaluating record linkage algorithms. Stat. Comput. 28(3), 539\u2013547 (2017). https:\/\/doi.org\/10.1007\/s11222-017-9746-6","journal-title":"Stat. Comput."},{"issue":"1","key":"26_CR10","first-page":"1282","volume":"2","author":"O Hassanzadeh","year":"2009","unstructured":"Hassanzadeh, O., Chiang, F., Lee, H., Miller, R.: Framework for evaluating clustering algorithms in duplicate detection. VLDB 2(1), 1282\u20131293 (2009)","journal-title":"VLDB"},{"key":"26_CR11","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-57454-7_44","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"Y Hu","year":"2017","unstructured":"Hu, Y., Wang, Q., Vatsalan, D., Christen, P.: Improving temporal record linkage using regression classification. In: Kim, J., Shim, K., Cao, L., Lee, J.-G., Lin, X., Moon, Y.-S. (eds.) PAKDD 2017, Part I. LNCS (LNAI), vol. 10234, pp. 561\u2013573. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-57454-7_44"},{"key":"26_CR12","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/978-981-15-1699-3_4","volume-title":"Data Mining","author":"N Kirielle","year":"2019","unstructured":"Kirielle, N., Christen, P., Ranbaduge, T.: Outlier detection based accurate geocoding of historical addresses. In: Le, T.D., et al. (eds.) AusDM 2019. CCIS, vol. 1127, pp. 41\u201353. Springer, Singapore (2019). https:\/\/doi.org\/10.1007\/978-981-15-1699-3_4"},{"key":"26_CR13","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139924801","volume-title":"Mining of Massive Datasets","author":"J Leskovec","year":"2014","unstructured":"Leskovec, J., Rajaraman, A., Ullman, J.D.: Mining of Massive Datasets. CUP, Cambridge (2014)"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Mudgal, S., Li, H., Rekatsinas, T., Doan, A., et al.: Deep learning for entity matching: a design space exploration. In: ACM SIGMOD, pp. 19\u201334. Houston (2018)","DOI":"10.1145\/3183713.3196926"},{"key":"26_CR15","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1007\/978-3-030-16145-3_41","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"C Nanayakkara","year":"2019","unstructured":"Nanayakkara, C., Christen, P., Ranbaduge, T.: Robust temporal graph clustering for group record linkage. In: Yang, Q., Zhou, Z.-H., Gong, Z., Zhang, M.-L., Huang, S.-J. (eds.) PAKDD 2019, Part II. LNCS (LNAI), vol. 11440, pp. 526\u2013538. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-16145-3_41"},{"issue":"2","key":"26_CR16","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.: Blocking and filtering techniques for entity resolution: a survey. ACM Comput. Surv. 53(2), 1\u201342 (2020)","journal-title":"ACM Comput. Surv."},{"key":"26_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1007\/978-3-030-49461-2_13","volume-title":"The Semantic Web","author":"A Primpeli","year":"2020","unstructured":"Primpeli, A., Bizer, C., Keuper, M.: Unsupervised bootstrapping of active learning for entity resolution. In: Harth, A., et al. (eds.) ESWC 2020. LNCS, vol. 12123, pp. 215\u2013231. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-49461-2_13"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Qian, K., Popa, L., Sen, P.: Active learning for large-scale entity resolution. In: ACM CIKM, pp. 1379\u20131388. Singapore (2017)","DOI":"10.1145\/3132847.3132949"},{"issue":"1\u20132","key":"26_CR19","doi-asserted-by":"publisher","first-page":"61","DOI":"10.3366\/hac.2002.14.1-2.61","volume":"14","author":"A Reid","year":"2002","unstructured":"Reid, A., Davies, R., Garrett, E.: Nineteenth-century Scottish demography from linked censuses and civil registers: a \u2018sets of related individuals\u2019 approach. Hist. Comput. 14(1\u20132), 61\u201386 (2002)","journal-title":"Hist. Comput."},{"key":"26_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"576","DOI":"10.1007\/978-3-319-93417-4_37","volume-title":"The Semantic Web","author":"A Saeedi","year":"2018","unstructured":"Saeedi, A., Peukert, E., Rahm, E.: Using link features for entity clustering in knowledge graphs. In: Gangemi, A., et al. (eds.) ESWC 2018. LNCS, vol. 10843, pp. 576\u2013592. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-93417-4_37"},{"key":"26_CR21","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1007\/978-3-319-93037-4_28","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"J Shao","year":"2018","unstructured":"Shao, J., Wang, Q.: Active blocking scheme learning for entity resolution. In: Phung, D., Tseng, V.S., Webb, G.I., Ho, B., Ganji, M., Rashidi, L. (eds.) PAKDD 2018, Part II. LNCS (LNAI), vol. 10938, pp. 350\u2013362. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-93037-4_28"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Tao, Y.: Entity matching with active monotone classification. In: ACM PODS, pp. 49\u201362. Houston (2018)","DOI":"10.1145\/3196959.3196984"},{"issue":"12","key":"26_CR23","first-page":"1071","volume":"7","author":"N Vesdapunt","year":"2014","unstructured":"Vesdapunt, N., Bellare, K., Dalvi, N.: Crowdsourcing algorithms for entity resolution. PVLDB 7(12), 1071\u20131082 (2014)","journal-title":"PVLDB"},{"key":"26_CR24","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1007\/978-3-319-18032-8_44","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"Q Wang","year":"2015","unstructured":"Wang, Q., Vatsalan, D., Christen, P.: Efficient interactive training selection for large-scale entity resolution. In: Cao, T., Lim, E.-P., Zhou, Z.-H., Ho, T.-B., Cheung, D., Motoda, H. (eds.) PAKDD 2015, Part II. LNCS (LNAI), vol. 9078, pp. 562\u2013573. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-18032-8_44"}],"container-title":["Lecture Notes in Computer Science","Advances in Knowledge Discovery and Data Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-75765-6_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,11]],"date-time":"2021-05-11T00:03:55Z","timestamp":1620691435000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-75765-6_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030757649","9783030757656"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-75765-6_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"8 May 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PAKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Asia Conference on Knowledge Discovery and Data Mining","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 May 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 May 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pakdd2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/pakdd2021.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"673","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"157","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"23% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}