{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T12:57:05Z","timestamp":1743080225241,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"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_9","type":"book-chapter","created":{"date-parts":[[2020,3,27]],"date-time":"2020-03-27T15:03:32Z","timestamp":1585321412000},"page":"101-111","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Linking IT Product Records"],"prefix":"10.1007","author":[{"given":"Katsiaryna","family":"Mirylenka","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paolo","family":"Scotton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christoph","family":"Miksovic","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salah-Eddine Bariol","family":"Alaoui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,3,28]]},"reference":[{"key":"9_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"244","DOI":"10.1007\/978-3-642-16367-8_16","volume-title":"Property Testing","author":"A Andoni","year":"2010","unstructured":"Andoni, A., Krauthgamer, R., Onak, K.: Polylogarithmic approximation for edit distance and the asymmetric query complexity. In: Goldreich, O. (ed.) Property Testing. LNCS, vol. 6390, pp. 244\u2013252. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-16367-8_16"},{"issue":"5","key":"9_CR2","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/MIS.2003.1234765","volume":"18","author":"M Bilenko","year":"2003","unstructured":"Bilenko, M., Mooney, R., Cohen, W., Ravikumar, P., Fienberg, S.: Adaptive name matching in information integration. IEEE Intell. Syst. 18(5), 16\u201323 (2003)","journal-title":"IEEE Intell. Syst."},{"key":"9_CR3","unstructured":"Cohen, W., Ravikumar, P., Fienberg, S.: A comparison of string metrics for matching names and records. In: KDD Workshop on Data Cleaning and Object Consolidation, vol. 3, pp. 73\u201378 (2003)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Cohen, W.W.: Integration of heterogeneous databases without common domains using queries based on textual similarity. In: ACM SIGMOD Record, vol. 27, pp. 201\u2013212. ACM (1998)","DOI":"10.1145\/276305.276323"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Dallachiesa, M., Nushi, B., Mirylenka, K., Palpanas, T.: Similarity matching for uncertain time series: analytical and experimental comparison. In: Proceedings of the 2nd ACM SIGSPATIAL International Workshop on Querying and Mining Uncertain Spatio-Temporal Data, pp. 8\u201315. ACM (2011)","DOI":"10.1145\/2064969.2064971"},{"issue":"11","key":"9_CR6","doi-asserted-by":"publisher","first-page":"1662","DOI":"10.14778\/2350229.2350278","volume":"5","author":"M Dallachiesa","year":"2012","unstructured":"Dallachiesa, M., Nushi, B., Mirylenka, K., Palpanas, T.: Uncertain time-series similarity: return to the basics. Proc. VLDB Endow. 5(11), 1662\u20131673 (2012)","journal-title":"Proc. VLDB Endow."},{"key":"9_CR7","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. CoRR abs\/1810.04805 (2018). http:\/\/arxiv.org\/abs\/1810.04805"},{"issue":"1","key":"9_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"AK Elmagarmid","year":"2007","unstructured":"Elmagarmid, A.K., Ipeirotis, P.G., Verykios, V.S.: Duplicate record detection: a survey. IEEE Trans. Knowl. Data Eng. 19(1), 1\u201316 (2007)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Gschwind, T., Miksovic, C., Mirylenka, K., Scotton, P.: Fast record linkage for company entities (2019). http:\/\/arxiv.org\/abs\/1907.08667","DOI":"10.1109\/BigData47090.2019.9006095"},{"key":"9_CR10","doi-asserted-by":"crossref","unstructured":"Hettiarachchi, G.P., Hettiarachchi, N.N., Hettiarachchi, D.S., Ebisuya, A.: Next generation data classification and linkage: role of probabilistic models and artificial intelligence. In: IEEE Global Humanitarian Technology Conference (GHTC 2014), pp. 569\u2013576 (2014)","DOI":"10.1109\/GHTC.2014.6970340"},{"issue":"406","key":"9_CR11","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1080\/01621459.1989.10478785","volume":"84","author":"MA Jaro","year":"1989","unstructured":"Jaro, M.A.: Advances in record-linkage methodology as applied to matching the 1985 census of Tampa, Florida. J. Am. Stat. Assoc. 84(406), 414\u2013420 (1989)","journal-title":"J. Am. Stat. Assoc."},{"issue":"8","key":"9_CR12","first-page":"707","volume":"10","author":"VI Levenshtein","year":"1966","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions and reversals. Soviet Physics Doklady 10(8), 707\u2013710 (1966)","journal-title":"Soviet Physics Doklady"},{"key":"9_CR13","unstructured":"Mirylenka, K.: Mining and learning in sequential data streams: interesting correlations and classification in noisy settings. Ph.D. thesis, University of Trento (2015)"},{"issue":"3","key":"9_CR14","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/s00778-015-0382-5","volume":"24","author":"K Mirylenka","year":"2015","unstructured":"Mirylenka, K., Cormode, G., Palpanas, T., Srivastava, D.: Conditional heavy hitters: detecting interesting correlations in data streams. VLDB J. Int. J. Very Large Data Bases 24(3), 395\u2013414 (2015)","journal-title":"VLDB J. Int. J. Very Large Data Bases"},{"key":"9_CR15","unstructured":"Mirylenka, K., Dallachiesa, M., Palpanas, T.: Correlation-aware distance measures for data series. In: EDBT, pp. 502\u2013505 (2017)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Mirylenka, K., Dallachiesa, M., Palpanas, T.: Data series similarity using correlation-aware measures. In: SSDBM 2017, pp. 11:1\u201311:12 (2017)","DOI":"10.1145\/3085504.3085515"},{"key":"9_CR17","unstructured":"Mirylenka, K., Miksovic, C., Scotton, P.: Applicability of latent Dirichlet allocation for company modeling. In: Industrial Conference on Data Mining (ICDM 2016) (2016)"},{"key":"9_CR18","unstructured":"Mirylenka, K., Miksovic, C., Scotton, P.: Recurrent neural networks for modeling company-product time series. In: Proceedings of AALTD, pp. 29\u201336 (2016)"},{"key":"9_CR19","doi-asserted-by":"crossref","unstructured":"Mirylenka, K., Palpanas, T., Cormode, G., Srivastava, D.: Finding interesting correlations with conditional heavy hitters. In: 2013 IEEE 29th International Conference on Data Engineering (ICDE), pp. 1069\u20131080. IEEE (2013)","DOI":"10.1109\/ICDE.2013.6544898"},{"key":"9_CR20","unstructured":"Mirylenka, K., Scotton, P., Miksovic, C., Dillon, J.: Hidden layer models for company representations and product recommendations. In: EDBT, pp. 468\u2013476 (2019)"},{"key":"9_CR21","unstructured":"Monge, A.E., Elkan, C., et al.: The field matching problem: algorithms and applications. In: KDD, vol. 2, pp. 267\u2013270 (1996)"},{"key":"9_CR22","unstructured":"Peters, M.E., et al.: Deep contextualized word representations. CoRR abs\/1802.05365 (2018). http:\/\/arxiv.org\/abs\/1802.05365"},{"key":"9_CR23","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language under-standing with unsupervised learning. Technical report, OpenAI (2018)"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Su, Z., Ahn, B.R., Eom, K.Y., Kang, M.K., Kim, J.P., Kim, M.K.: Plagiarism detection using the levenshtein distance and Smith-Waterman algorithm. In: ICICIC 2008, pp. 569\u2013569. IEEE (2008)","DOI":"10.1109\/ICICIC.2008.422"},{"issue":"2","key":"9_CR25","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1145\/1328854.1328855","volume":"36","author":"S Tata","year":"2007","unstructured":"Tata, S., Patel, J.M.: Estimating the selectivity of tf-idf based cosine similarity predicates. SIGMOD Rec. 36(2), 7\u201312 (2007)","journal-title":"SIGMOD Rec."},{"key":"9_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/978-3-642-17289-2_45","volume-title":"Advances in Visual Computing","author":"A Uhl","year":"2010","unstructured":"Uhl, A., Wild, P.: Enhancing iris matching using Levenshtein Distance with alignment constraints. In: Bebis, G., et al. (eds.) ISVC 2010. LNCS, vol. 6453, pp. 469\u2013478. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-17289-2_45"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Wilson, D.R.: Beyond probabilistic record linkage: using neural networks and complex features to improve genealogical record linkage. In: The 2011 International Joint Conference on Neural Networks, pp. 9\u201314 (2011)","DOI":"10.1109\/IJCNN.2011.6033192"},{"key":"9_CR28","unstructured":"Winkler, W.E.: String comparator metrics and enhanced decision rules in the Fellegi-Sunter model of record linkage. In: Proceedings of the Section on Survey Research, pp. 354\u2013359 (1990)"}],"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_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T01:04:16Z","timestamp":1707786256000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-43887-6_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030438869","9783030438876"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-43887-6_9","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"}]}}