{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T22:19:14Z","timestamp":1755037154170,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030438869"},{"type":"electronic","value":"9783030438876"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-43887-6_11","type":"book-chapter","created":{"date-parts":[[2020,3,27]],"date-time":"2020-03-27T15:03:32Z","timestamp":1585321412000},"page":"125-141","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Informativeness-Based Active Learning for Entity Resolution"],"prefix":"10.1007","author":[{"given":"Victor","family":"Christen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Christen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erhard","family":"Rahm","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,28]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Arasu, A., G\u00f6tz, M., Kaushik, R.: On active learning of record matching packages. In: ACM SIGMOD, Indianapolis, pp. 783\u2013794 (2010)","DOI":"10.1145\/1807167.1807252"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Bellare, K., Iyengar, S., Parameswaran, A.G., Rastogi, V.: Active sampling for entity matching. In: ACM SIGKDD, Beijing, pp. 1131\u20131139 (2012)","DOI":"10.1145\/2339530.2339707"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Christen, P.: Automatic record linkage using seeded nearest neighbour and support vector machine classification. In: ACM SIGKDD, Las Vegas, pp. 151\u2013159 (2008)","DOI":"10.1145\/1401890.1401913"},{"key":"11_CR4","series-title":"Data-Centric Systems and Applications","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.: Data Matching - Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection. Data-Centric Systems and Applications. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31164-2"},{"issue":"19","key":"11_CR5","doi-asserted-by":"publisher","first-page":"1767","DOI":"10.1016\/j.tcs.2010.12.054","volume":"412","author":"S Dasgupta","year":"2011","unstructured":"Dasgupta, S.: Two faces of active learning. Theoret. Comput. Sci. 412(19), 1767\u20131781 (2011)","journal-title":"Theoret. Comput. Sci."},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Ertekin, S., Huang, J., Bottou, L., Giles, L.: Learning on the border: active learning in imbalanced data classification. In: ACM CIKM, Lisbon, pp. 127\u2013136 (2007)","DOI":"10.1145\/1321440.1321461"},{"key":"11_CR7","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1007\/978-0-387-09823-4_66","volume-title":"Data Mining and Knowledge Discovery Handbook","author":"E Frank","year":"2009","unstructured":"Frank, E., et al.: Weka-a machine learning workbench for data mining. In: Maimon, O., Rokach, L. (eds.) Data Mining and Knowledge Discovery Handbook, pp. 1269\u20131277. Springer, Boston (2009). https:\/\/doi.org\/10.1007\/978-0-387-09823-4_66"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Gokhale, C., et al.: Corleone: hands-off crowdsourcing for entity matching. In: ACM SIGMOD, Snowbird, Utah, pp. 601\u2013612 (2014)","DOI":"10.1145\/2588555.2588576"},{"issue":"3","key":"11_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."},{"key":"11_CR10","doi-asserted-by":"publisher","unstructured":"Hildebrandt, K., Panse, F., Wilcke, N., Ritter, N.: Large-scale data pollution with apache spark. IEEE Trans. Big Data 1 (2017). https:\/\/doi.org\/10.1109\/TBDATA.2016.2637378. ISSN 2372-2096","DOI":"10.1109\/TBDATA.2016.2637378"},{"issue":"2","key":"11_CR11","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.: Frameworks for entity matching: a comparison. Data Knowl. Eng. 69(2), 197\u2013210 (2010)","journal-title":"Data Knowl. Eng."},{"issue":"1\u20132","key":"11_CR12","doi-asserted-by":"publisher","first-page":"484","DOI":"10.14778\/1920841.1920904","volume":"3","author":"H K\u00f6pcke","year":"2010","unstructured":"K\u00f6pcke, H., Thor, A., Rahm, E.: Evaluation of entity resolution approaches on real-world match problems. PVLDB Endow. 3(1\u20132), 484\u2013493 (2010)","journal-title":"PVLDB Endow."},{"key":"11_CR13","unstructured":"K\u00f6pcke, H., Rahm, E.: Training selection for tuning entity matching. In: QDB\/MUD, Auckland, pp. 3\u201312 (2008)"},{"issue":"4","key":"11_CR14","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/MIC.2010.58","volume":"14","author":"H K\u00f6pcke","year":"2010","unstructured":"K\u00f6pcke, H., Thor, A., Rahm, E.: Learning-based approaches for matching web data entities. IEEE Internet Comput. 14(4), 23\u201331 (2010)","journal-title":"IEEE Internet Comput."},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"McCallum, A., Nigam, K., Ungar, L.H.: Efficient clustering of high-dimensional data sets with application to reference matching. In: ACM SIGKDD, Boston, pp. 169\u2013178 (2000)","DOI":"10.1145\/347090.347123"},{"issue":"2","key":"11_CR16","doi-asserted-by":"publisher","first-page":"125","DOI":"10.14778\/2735471.2735474","volume":"8","author":"B Mozafari","year":"2014","unstructured":"Mozafari, B., Sarkar, P., Franklin, M., Jordan, M., Madden, S.: Scaling up crowd-sourcing to very large datasets: a case for active learning. PVLDB Endow. 8(2), 125\u2013136 (2014)","journal-title":"PVLDB Endow."},{"key":"11_CR17","series-title":"Synthesis Lectures on Data Management","doi-asserted-by":"publisher","DOI":"10.2200\/S00262ED1V01Y201003DTM003","volume-title":"An Introduction to Duplicate Detection","author":"F Naumann","year":"2010","unstructured":"Naumann, F., Herschel, M.: An Introduction to Duplicate Detection. Synthesis Lectures on Data Management. Morgan and Claypool Publishers, San Rafael (2010)"},{"key":"11_CR18","doi-asserted-by":"publisher","first-page":"419","DOI":"10.3233\/SW-150210","volume":"8","author":"M Nentwig","year":"2017","unstructured":"Nentwig, M., Hartung, M., Ngonga Ngomo, A.C., Rahm, E.: A survey of current link discovery frameworks. Semant. Web 8, 419\u2013436 (2017)","journal-title":"Semant. Web"},{"key":"11_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/978-3-642-30284-8_17","volume-title":"The Semantic Web: Research and Applications","author":"A-C Ngonga Ngomo","year":"2012","unstructured":"Ngonga Ngomo, A.-C., Lyko, K.: EAGLE: efficient active learning of link specifications using genetic programming. In: Simperl, E., Cimiano, P., Polleres, A., Corcho, O., Presutti, V. (eds.) ESWC 2012. LNCS, vol. 7295, pp. 149\u2013163. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-30284-8_17"},{"issue":"4","key":"11_CR20","first-page":"3","volume":"23","author":"E Rahm","year":"2000","unstructured":"Rahm, E., Do, H.H.: Data cleaning: problems and current approaches. IEEE Data Eng. Bull. 23(4), 3\u201313 (2000)","journal-title":"IEEE Data Eng. Bull."},{"key":"11_CR21","unstructured":"Settles, B.: Active learning literature survey. Technical report, University of Wisconsin-Madison, Department of Computer Sciences (2009)"},{"key":"11_CR22","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","volume":"27","author":"CE Shannon","year":"1948","unstructured":"Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 27, 379\u2013423 (1948)","journal-title":"Bell Syst. Tech. J."},{"key":"11_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/978-3-319-58068-5_7","volume-title":"The Semantic Web","author":"MA Sherif","year":"2017","unstructured":"Sherif, M.A., Ngonga Ngomo, A.-C., Lehmann, J.: Wombat \u2013 a generalization approach for automatic link discovery. In: Blomqvist, E., Maynard, D., Gangemi, A., Hoekstra, R., Hitzler, P., Hartig, O. (eds.) ESWC 2017. LNCS, vol. 10249, pp. 103\u2013119. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-58068-5_7"},{"issue":"2","key":"11_CR24","first-page":"189","volume":"11","author":"R Singh","year":"2017","unstructured":"Singh, R., et al.: Synthesizing entity matching rules by examples. PVLDB 11(2), 189\u2013202 (2017)","journal-title":"PVLDB"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Tsai, M.H., Ho, C.H., Lin, C.J.: Active learning strategies using SVMs. In: The 2010 International Joint Conference on Neural Networks (IJCNN), Barcelona, pp. 1\u20138. IEEE (2010)","DOI":"10.1109\/IJCNN.2010.5596668"},{"key":"11_CR26","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. LNCS (LNAI), vol. 9078, pp. 562\u2013573. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-18032-8_44"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Wang, S., Xiao, X., Lee, C.H.: Crowd-based deduplication: an adaptive approach. In: ACM SIGMOD, Melbourne, pp. 1263\u20131277 (2015)","DOI":"10.1145\/2723372.2723739"}],"container-title":["Communications in Computer and Information Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-43887-6_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T01:04:25Z","timestamp":1707786265000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-43887-6_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030438869","9783030438876"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-43887-6_11","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"28 March 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"W\u00fcrzburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ecmlpkdd2019.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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"733","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":"130","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":"18% - 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":"3.04","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":"5.3","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)"}},{"value":"ECML PKDD Workshops Information: single-blind review, submissions: 200, full papers accepted: 70, short papers accepted: 46","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}