{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T11:26:32Z","timestamp":1773487592233,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2020,2,13]],"date-time":"2020-02-13T00:00:00Z","timestamp":1581552000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,2,13]],"date-time":"2020-02-13T00:00:00Z","timestamp":1581552000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1007\/s10462-020-09807-8","type":"journal-article","created":{"date-parts":[[2020,2,13]],"date-time":"2020-02-13T19:03:50Z","timestamp":1581620630000},"page":"4777-4820","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["A self-verifying clustering approach to unsupervised matching of product titles"],"prefix":"10.1007","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6602-0723","authenticated-orcid":false,"given":"Leonidas","family":"Akritidis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Athanasios","family":"Fevgas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panayiotis","family":"Bozanis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christos","family":"Makris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,2,13]]},"reference":[{"key":"9807_CR1","doi-asserted-by":"crossref","unstructured":"Akritidis L, Bozanis P (2018) Effective unsupervised matching of product titles with k-combinations and permutations. In: Proceedings of the 14th IEEE international conference on innovations in intelligent systems and applications (INISTA), pp 1\u201310","DOI":"10.1109\/INISTA.2018.8466294"},{"key":"9807_CR2","unstructured":"B\u00e4r D, Biemann C, Gurevych I, Zesch T (2012) UKP: computing semantic textual similarity by combining multiple content similarity measures. In: Proceedings of the 1st joint conference on lexical and computational semantics, pp 435\u2013440"},{"key":"9807_CR3","doi-asserted-by":"crossref","unstructured":"Bilenko M, Mooney RJ (2003) Adaptive duplicate detection using learnable string similarity measures. In: Proceedings of the 9th ACM international conference on knowledge discovery and data mining (SIGKDD), pp 39\u201348","DOI":"10.1145\/956750.956759"},{"key":"9807_CR4","doi-asserted-by":"crossref","unstructured":"Chaudhuri S, Ganjam K, Ganti V, Motwani R (2003) Robust and efficient fuzzy match for online data cleaning. In: Proceedings of the 2003 ACM international conference on management of data (SIGMOD), pp 313\u2013324","DOI":"10.1145\/872757.872796"},{"key":"9807_CR5","unstructured":"Christen P (2008) FEBRL: a freely available record linkage system with a graphical user interface. In: Proceedings of the 2nd Australasian workshop on health data and knowledge management, pp 17\u201325"},{"key":"9807_CR6","doi-asserted-by":"crossref","unstructured":"de\u00a0Bakker M, Frasincar F, Vandic D (2013) A hybrid model words-driven approach for web product duplicate detection. In: Proceedings of the international conference on advanced information systems engineering, pp 149\u2013161","DOI":"10.1007\/978-3-642-38709-8_10"},{"issue":"11","key":"9807_CR7","doi-asserted-by":"publisher","first-page":"1944","DOI":"10.1109\/TPAMI.2007.1115","volume":"29","author":"IS Dhillon","year":"2007","unstructured":"Dhillon IS, Guan Y, Kulis B (2007) Weighted graph cuts without eigenvectors a multilevel approach. IEEE Trans Pattern Anal Mach Intell 29(11):1944\u20131957","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"9807_CR8","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1080\/01969727308546046","volume":"3","author":"JC Dunn","year":"1973","unstructured":"Dunn JC (1973) A fuzzy relative of the isodata process and its use in detecting compact well-separated clusters. J Cybernet 3(3):32\u201357","journal-title":"J Cybernet"},{"issue":"1","key":"9807_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TKDE.2007.250581","volume":"19","author":"AK Elmagarmid","year":"2007","unstructured":"Elmagarmid AK, Ipeirotis PG, Verykios VS (2007) Duplicate record detection: a survey. IEEE Trans Knowl Data Eng 19(1):1\u201316","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"9807_CR10","unstructured":"Ester M, Kriegel HP, Sander J, Xu X, et\u00a0al. (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of the 2nd international confernece on knowledge discovery and data mining (KDD), pp 226\u2013231"},{"issue":"1","key":"9807_CR11","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1016\/j.patcog.2007.05.018","volume":"41","author":"M Filippone","year":"2008","unstructured":"Filippone M, Camastra F, Masulli F, Rovetta S (2008) A survey of kernel and spectral methods for clustering. Pattern Recognit 41(1):176\u2013190","journal-title":"Pattern Recognit"},{"issue":"13","key":"9807_CR12","first-page":"13","volume":"68","author":"WH Gomaa","year":"2013","unstructured":"Gomaa WH, Fahmy AA (2013) A survey of text similarity approaches. Int J Comput Appl 68(13):13\u201318","journal-title":"Int J Comput Appl"},{"key":"9807_CR13","doi-asserted-by":"crossref","unstructured":"Gopalakrishnan V, Iyengar SP, Madaan A, Rastogi R, Sengamedu S (2012) Matching product titles using web-based enrichment. In: Proceedings of the 21st ACM international conference on information and knowledge management (CIKM), pp 605\u2013614","DOI":"10.1145\/2396761.2396839"},{"key":"9807_CR14","doi-asserted-by":"crossref","unstructured":"Hua W, Wang Z, Wang H, Zheng K, Zhou X (2015) Short text understanding through lexical-semantic analysis. In: Proceedings of the 31st IEEE international conference on data engineering, pp 495\u2013506","DOI":"10.1109\/ICDE.2015.7113309"},{"issue":"2","key":"9807_CR15","first-page":"10","volume":"2","author":"A Islam","year":"2008","unstructured":"Islam A, Inkpen D (2008) Semantic Text Similarity using Corpus-Based Word Similarity and String Similarity. ACM Trans Knowl Discov Data (TKDD) 2(2):10","journal-title":"ACM Trans Knowl Discov Data (TKDD)"},{"issue":"3","key":"9807_CR16","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"AK Jain","year":"1999","unstructured":"Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv (CSUR) 31(3):264\u2013323","journal-title":"ACM Comput Surv (CSUR)"},{"key":"9807_CR17","doi-asserted-by":"crossref","unstructured":"K\u00f6pcke H, Thor A, Thomas S, Rahm E (2012) Tailoring entity resolution for matching product offers. In: Proceedings of the 15th international conference on extending database technology, pp 545\u2013550","DOI":"10.1145\/2247596.2247662"},{"key":"9807_CR18","doi-asserted-by":"crossref","unstructured":"Li C, Lu J, Lu Y (2008) Efficient merging and filtering algorithms for approximate string searches. In: Proceedings of the 24th IEEE international conference on data engineering (ICDE), pp 257\u2013266","DOI":"10.1109\/ICDE.2008.4497434"},{"issue":"12","key":"9807_CR19","doi-asserted-by":"publisher","first-page":"1167","DOI":"10.14778\/2732977.2732990","volume":"7","author":"N Londhe","year":"2014","unstructured":"Londhe N, Gopalakrishnan V, Zhang A, Ngo HQ, Srihari R (2014) Matching titles with cross title web-search enrichment and community detection. Proc VLDB Endow 7(12):1167\u20131178","journal-title":"Proc VLDB Endow"},{"key":"9807_CR20","unstructured":"Lu W, Robertson S, MacFarlane A (2005) Field-weighted XML retrieval based on BM25. In: Proceedings of international workshop of the initiative for the evaluation of XML retrieval, pp 161\u2013171"},{"key":"9807_CR21","doi-asserted-by":"crossref","unstructured":"Lu J, Lin C, Wang W, Li C, Wang H (2013) String similarity measures and joins with synonyms. In: Proceedings of the ACM international conference on management of data (SIGMOD), pp 373\u2013384","DOI":"10.1145\/2463676.2465313"},{"key":"9807_CR22","unstructured":"MacQueen J, et\u00a0al. (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the 5th Berkeley symposium on mathematical statistics and probability vol 1, no 14, pp 281\u2013297"},{"key":"9807_CR23","doi-asserted-by":"crossref","unstructured":"Manning CD, Raghavan P, Sch\u00fctze H (2008) Introduction to information retrieval. Cambridge University Press, Cambridge","DOI":"10.1017\/CBO9780511809071"},{"key":"9807_CR24","unstructured":"Ng AY, Jordan MI, Weiss Y (2002) On spectral clustering: analysis and an algorithm. In: Proceedings of advances in neural information processing systems, pp 849\u2013856"},{"key":"9807_CR25","doi-asserted-by":"crossref","unstructured":"Shen W, DeRose P, Vu L, Doan A, Ramakrishnan R (2007) Source-aware entity matching: a compositional approach. In: Proceedings of the 23rd IEEE international conference on data engineering (ICDE), pp 196\u2013205","DOI":"10.1109\/ICDE.2007.367865"},{"issue":"1","key":"9807_CR26","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1099\/00221287-17-1-201","volume":"17","author":"PH Sneath","year":"1957","unstructured":"Sneath PH (1957) The application of computers to taxonomy. Microbiology 17(1):201\u2013226","journal-title":"Microbiology"},{"key":"9807_CR27","first-page":"1","volume":"5","author":"TA Sorensen","year":"1948","unstructured":"Sorensen TA (1948) A method of establishing groups of equal amplitude in plant sociology based on similarity of species content and its application to analyses of the vegetation on danish commons. Biologiske Skrifter 5:1\u201334","journal-title":"Biologiske Skrifter"},{"key":"9807_CR28","doi-asserted-by":"crossref","unstructured":"Wang J, Li G, Fe J (2011a) Fast-join: An efficient method for fuzzy token matching based string similarity join. In: Proceedings of the 27th IEEE international conference on data engineering (ICDE), pp 458\u2013469","DOI":"10.1109\/ICDE.2011.5767865"},{"issue":"10","key":"9807_CR29","doi-asserted-by":"publisher","first-page":"622","DOI":"10.14778\/2021017.2021020","volume":"4","author":"J Wang","year":"2011","unstructured":"Wang J, Li G, Yu JX, Feng J (2011b) Entity matching: how similar is similar. Proc VLDB Endow 4(10):622\u2013633","journal-title":"Proc VLDB Endow"},{"issue":"3","key":"9807_CR30","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1145\/2000824.2000825","volume":"36","author":"C Xiao","year":"2011","unstructured":"Xiao C, Wang W, Lin X, Yu JX, Wang G (2011) Efficient similarity joins for near-duplicate detection. ACM Trans Database Syst 36(3):15","journal-title":"ACM Trans Database Syst"},{"issue":"3","key":"9807_CR31","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1109\/TNN.2005.845141","volume":"16","author":"R Xu","year":"2005","unstructured":"Xu R, Wunsch DC (2005) Survey of clustering algorithms. IEEE Trans Neural Netw 16(3):645\u2013678","journal-title":"IEEE Trans Neural Netw"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-020-09807-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-020-09807-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-020-09807-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,12]],"date-time":"2021-02-12T00:14:26Z","timestamp":1613088866000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-020-09807-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,13]]},"references-count":31,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["9807"],"URL":"https:\/\/doi.org\/10.1007\/s10462-020-09807-8","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,13]]},"assertion":[{"value":"13 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}