{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,27]],"date-time":"2025-07-27T07:44:43Z","timestamp":1753602283589,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031221361"},{"type":"electronic","value":"9783031221378"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-22137-8_28","type":"book-chapter","created":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T04:36:29Z","timestamp":1669178189000},"page":"379-391","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deduplication Over\u00a0Heterogeneous Attribute Types (D-HAT)"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1910-5403","authenticated-orcid":false,"given":"Loujain","family":"Liekah","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7298-9431","authenticated-orcid":false,"given":"George","family":"Papadakis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,24]]},"reference":[{"key":"28_CR1","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1162\/tacl_a_00051","volume":"5","author":"P Bojanowski","year":"2017","unstructured":"Bojanowski, P., et al.: Enriching word vectors with subword information. Trans. Assoc. Comput. Linguist. 5, 135\u2013146 (2017)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"28_CR2","unstructured":"Brunner, U., Stockinger, K.: Entity matching with transformer architectures - a step forward in data integration. In: EDBT, pp. 463\u2013473 (2020)"},{"issue":"2","key":"28_CR3","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s11036-013-0489-0","volume":"19","author":"M Chen","year":"2014","unstructured":"Chen, M., Mao, S., Liu, Y.: Big data: a survey. Mob. Netw. Appl. 19(2), 171\u2013209 (2014). https:\/\/doi.org\/10.1007\/s11036-013-0489-0","journal-title":"Mob. Netw. Appl."},{"key":"28_CR4","doi-asserted-by":"publisher","unstructured":"Christen, P.: The data matching process. In: Data Matching. Data-Centric Systems and Applications. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-31164-2_2","DOI":"10.1007\/978-3-642-31164-2_2"},{"issue":"9","key":"28_CR5","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1109\/TKDE.2011.127","volume":"24","author":"P Christen","year":"2012","unstructured":"Christen, P.: A survey of indexing techniques for scalable record linkage and deduplication. IEEE Trans. Knowl. Data Eng. 24(9), 1537\u20131555 (2012)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"6","key":"28_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3418896","volume":"53","author":"V Christophides","year":"2021","unstructured":"Christophides, V., Efthymiou, V., Palpanas, T., Papadakis, G., Stefanidis, K.: An overview of end-to-end entity resolution for big data. ACM Comput. Surv. 53(6), 1\u201342 (2021)","journal-title":"ACM Comput. Surv."},{"key":"28_CR7","unstructured":"Devlin, J., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT, pp. 4171\u20134186 (2019)"},{"issue":"1","key":"28_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-01853-4","volume":"7","author":"XL Dong","year":"2015","unstructured":"Dong, X.L., Srivastava, D.: Big data integration. Synth. Lect. Data Manag. 7(1), 1\u2013198 (2015)","journal-title":"Synth. Lect. Data Manag."},{"issue":"4","key":"28_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2567657","volume":"4","author":"W Fan","year":"2014","unstructured":"Fan, W., Ma, S., Tang, N., Yu, W.: Interaction between record matching and data repairing. J. Data Inf. Qual. 4(4), 1\u201338 (2014)","journal-title":"J. Data Inf. Qual."},{"issue":"328","key":"28_CR10","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1080\/01621459.1969.10501049","volume":"64","author":"IP Fellegi","year":"1969","unstructured":"Fellegi, I.P., Sunter, A.B.: A theory for record linkage. J. Am. Stat. Assoc. 64(328), 1183\u20131210 (1969)","journal-title":"J. Am. Stat. Assoc."},{"issue":"12","key":"28_CR11","doi-asserted-by":"publisher","first-page":"2018","DOI":"10.14778\/2367502.2367564","volume":"5","author":"L Getoor","year":"2012","unstructured":"Getoor, L., Machanavajjhala, A.: Entity resolution: theory, practice & open challenges. Proc. VLDB Endow. 5(12), 2018\u20132019 (2012)","journal-title":"Proc. VLDB Endow."},{"issue":"1","key":"28_CR12","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.14778\/1687627.1687771","volume":"2","author":"O Hassanzadeh","year":"2009","unstructured":"Hassanzadeh, O., et al.: Framework for evaluating clustering algorithms in duplicate detection. Proc. VLDB Endow. 2(1), 1282\u20131293 (2009)","journal-title":"Proc. VLDB Endow."},{"issue":"12","key":"28_CR13","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.14778\/2994509.2994535","volume":"9","author":"P Konda","year":"2016","unstructured":"Konda, P., Das, S., et al.: Magellan: toward building entity matching management systems. Proc. VLDB Endow. 9(12), 1197\u20131208 (2016)","journal-title":"Proc. VLDB Endow."},{"key":"28_CR14","unstructured":"Kusner, M.J., Sun, Y., Kolkin, N.I., Weinberger, K.Q.: From word embeddings to document distances. In: ICML, vol. 37, pp. 957\u2013966 (2015)"},{"issue":"1","key":"28_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3431816","volume":"13","author":"Y Li","year":"2021","unstructured":"Li, Y., Li, J., Suhara, Y., Wang, J., Hirota, W., Tan, W.: Deep entity matching: challenges and opportunities. ACM J. Data Inf. Qual. 13(1), 1\u201317 (2021)","journal-title":"ACM J. Data Inf. Qual."},{"key":"28_CR16","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Mudgal, S., et al.: Deep learning for entity matching: a design space exploration. In: SIGMOD, pp. 19\u201334 (2018)","DOI":"10.1145\/3183713.3196926"},{"key":"28_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2020.101565","volume":"93","author":"G Papadakis","year":"2020","unstructured":"Papadakis, G., et al.: Three-dimensional entity resolution with JedAI. Inf. Syst. 93, 101565 (2020)","journal-title":"Inf. Syst."},{"issue":"2","key":"28_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3377455","volume":"53","author":"G Papadakis","year":"2020","unstructured":"Papadakis, G., et al.: Blocking and filtering techniques for entity resolution: a survey. ACM Comput. Surv. 53(2), 1\u201342 (2020)","journal-title":"ACM Comput. Surv."},{"issue":"9","key":"28_CR20","doi-asserted-by":"publisher","first-page":"684","DOI":"10.14778\/2947618.2947624","volume":"9","author":"G Papadakis","year":"2016","unstructured":"Papadakis, G., et al.: Comparative analysis of approximate blocking techniques for entity resolution. Proc. VLDB Endow. 9(9), 684\u2013695 (2016)","journal-title":"Proc. VLDB Endow."},{"issue":"12","key":"28_CR21","doi-asserted-by":"publisher","first-page":"1950","DOI":"10.14778\/3229863.3236232","volume":"11","author":"G Papadakis","year":"2018","unstructured":"Papadakis, G., et al.: The return of JedAI: end-to-end entity resolution for structured and semi-structured data. Proc. VLDB Endow. 11(12), 1950\u20131953 (2018)","journal-title":"Proc. VLDB Endow."},{"key":"28_CR22","doi-asserted-by":"crossref","unstructured":"Wang, J., Kraska, T., Franklin, M.J., Feng, J.: CrowdER: crowdsourcing entity resolution. arXiv preprint arXiv:1208.1927 (2012)","DOI":"10.14778\/2350229.2350263"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Z., Sisman, B., Wei, H., Dong, X.L., Ji, S.: CorDEL: a contrastive deep learning approach for entity linkage. In: ICDM, pp. 1322\u20131327 (2020)","DOI":"10.1109\/ICDM50108.2020.00171"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Wu, R., Chaba, S., Sawlani, S., Chu, X., Thirumuruganathan, S.: ZeroER: entity resolution using zero labeled examples. In: SIGMOD, pp. 1149\u20131164 (2020)","DOI":"10.1145\/3318464.3389743"}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-22137-8_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,23]],"date-time":"2022-11-23T08:08:59Z","timestamp":1669190939000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-22137-8_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031221361","9783031221378"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-22137-8_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"24 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brisbane, QLD","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"adma2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2022.uqcloud.net\/index.html","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":"CMT3","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"198","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":"72","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":"36% - 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":"5","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":"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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}