{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,6,17]],"date-time":"2024-06-17T07:11:56Z","timestamp":1718608316136},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,1,14]],"date-time":"2015-01-14T00:00:00Z","timestamp":1421193600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2016,2]]},"DOI":"10.1007\/s10115-015-0818-7","type":"journal-article","created":{"date-parts":[[2015,1,13]],"date-time":"2015-01-13T02:18:56Z","timestamp":1421115536000},"page":"285-314","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Efficient entity resolution based on subgraph cohesion"],"prefix":"10.1007","volume":"46","author":[{"given":"Hongzhi","family":"Wang","sequence":"first","affiliation":[]},{"given":"Jianzhong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Hong","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,1,14]]},"reference":[{"key":"818_CR1","unstructured":"Duplicate detection, record linkage, and identity uncertainty: datasets. http:\/\/www.cs.utexas.edu\/users\/ml\/riddle\/data.html . Accessed 6 Oct 2013"},{"key":"818_CR2","unstructured":"Matching (graph theory) (2012). http:\/\/en.wikipedia.org\/matching_(graph_theory) . Accessed 15 Oct 2012"},{"key":"818_CR3","unstructured":"DBLP (2014). http:\/\/www.informatik.uni-trier.de\/~ley\/db\/ . Accessed 15 Jan 2014"},{"key":"818_CR4","doi-asserted-by":"crossref","unstructured":"Arasu A, R\u00e9 C, Suciu D (2009) Large-scale deduplication with constraints using dedupalog. In: ICDE, pp 952\u2013963","DOI":"10.1109\/ICDE.2009.43"},{"key":"818_CR5","doi-asserted-by":"crossref","first-page":"95","DOI":"10.7155\/jgaa.00084","volume":"8","author":"JA Aslam","year":"2004","unstructured":"Aslam JA, Pelekhov E, Rus D (2004) The star clustering algorithm for static and dynamic information organization. J Graph Algorithms Appl 8:95\u2013129","journal-title":"J Graph Algorithms Appl"},{"key":"818_CR6","doi-asserted-by":"crossref","unstructured":"Bayardo RJ, Ma Y, Srikant R (2007) Scaling up all pairs similarity search. In: WWW, pp 131\u2013140","DOI":"10.1145\/1242572.1242591"},{"issue":"1","key":"818_CR7","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1007\/s00778-008-0098-x","volume":"18","author":"O Benjelloun","year":"2009","unstructured":"Benjelloun O, Garcia-Molina H, Menestrina D, Su Q, Whang SE, Widom J (2009) Swoosh: a generic approach to entity resolution. VLDB J 18(1):255\u2013276","journal-title":"VLDB J"},{"key":"818_CR8","doi-asserted-by":"crossref","unstructured":"Bhattacharya I, Getoor L (2004) Iterative record linkage for cleaning and integration. In: DMKD, pp 11\u201318","DOI":"10.1145\/1008694.1008697"},{"key":"818_CR9","unstructured":"Chaudhuri S, Chen B-C, Ganti V, Kaushik R (2007) Example-driven design of efficient record matching queries. In: VLDB, pp 327\u2013338"},{"key":"818_CR10","doi-asserted-by":"crossref","unstructured":"Chaudhuri S, Ganti V, Kaushik R (2006) A primitive operator for similarity joins in data cleaning. In: ICDE, p 5","DOI":"10.1109\/ICDE.2006.9"},{"key":"818_CR11","doi-asserted-by":"crossref","unstructured":"Chaudhuri S, Sarma AD, Ganti V, Kaushik R (2007) Leveraging aggregate constraints for deduplication. In: SIGMOD conference, pp 437\u2013448","DOI":"10.1145\/1247480.1247530"},{"key":"818_CR12","doi-asserted-by":"crossref","unstructured":"Chen Z, Kalashnikov DV, Mehrotra S (2009) Exploiting context analysis for combining multiple entity resolution systems. In: SIGMOD conference, pp 207\u2013218","DOI":"10.1145\/1559845.1559869"},{"key":"818_CR13","doi-asserted-by":"crossref","unstructured":"Dong X, Halevy AY, Madhavan J (2005) Reference reconciliation in complex information spaces. In: SIGMOD conference, pp 85\u201396","DOI":"10.1145\/1066157.1066168"},{"key":"818_CR14","volume-title":"Pattern classification","author":"R Duda","year":"2001","unstructured":"Duda R, Hart P, Stork D (2001) Pattern classification. Wiley, Hoboken, NJ"},{"issue":"1","key":"818_CR15","doi-asserted-by":"crossref","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"},{"issue":"1","key":"818_CR16","first-page":"1282","volume":"2","author":"O Hassanzadeh","year":"2009","unstructured":"Hassanzadeh O, Chiang F, Miller RJ, Lee HC (2009) Framework for evaluating clustering algorithms in duplicate detection. PVLDB 2(1):1282\u20131293","journal-title":"PVLDB"},{"issue":"5","key":"818_CR17","doi-asserted-by":"crossref","first-page":"1141","DOI":"10.1007\/s00778-009-0161-2","volume":"18","author":"O Hassanzadeh","year":"2009","unstructured":"Hassanzadeh O, Miller RJ (2009) Creating probabilistic databases from duplicated data. VLDB J 18(5):1141\u20131166","journal-title":"VLDB J"},{"key":"818_CR18","doi-asserted-by":"crossref","unstructured":"Jiang Y, Li G, Feng J, Li W (2014) String similarity joins: an experimental evaluation. PVLDB 7(8):625\u2013636","DOI":"10.14778\/2732296.2732299"},{"issue":"2","key":"818_CR19","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1145\/1138394.1138401","volume":"31","author":"DV Kalashnikov","year":"2006","unstructured":"Kalashnikov DV, Mehrotra S (2006) Domain-independent data cleaning via analysis of entity-relationship graph. ACM Trans Database Syst 31(2):716\u2013767","journal-title":"ACM Trans Database Syst"},{"key":"818_CR20","doi-asserted-by":"crossref","unstructured":"Kim HS, Lee D (2010) Harra: fast iterative hashed record linkage for large-scale data collections. In: EDBT, pp 525\u2013536","DOI":"10.1145\/1739041.1739104"},{"key":"818_CR21","doi-asserted-by":"crossref","unstructured":"Koudas N, Saha A, Srivastava D, Venkatasubramanian S (2009) Metric functional dependencies. In: ICDE, pp 1275\u20131278","DOI":"10.1109\/ICDE.2009.219"},{"key":"818_CR22","volume-title":"Foundations of statistical natural language processing","author":"CD Manning","year":"1999","unstructured":"Manning CD, Sch\u00fctze H (1999) Foundations of statistical natural language processing. The MIT Press, Cambridge, MA"},{"key":"818_CR23","doi-asserted-by":"crossref","unstructured":"Menestrina D, Whang S, Garcia-Molina H (2010) Evaluating entity resolution results. PVLDB 3(1):208\u2013219","DOI":"10.14778\/1920841.1920871"},{"key":"818_CR24","unstructured":"Micali S, Vazirani VV (1980) An $$\\text{ o }(\\sqrt{|V|}|e|$$ o ( | V | | e | ) algorithm for finding maximum matching in general graphs. In: FOCS, pp 17\u201327"},{"key":"818_CR25","unstructured":"Michelson M, Knoblock CA (2006) Learning blocking schemes for record linkage. In: AAAI"},{"key":"818_CR26","unstructured":"Michelson M, Knoblock CA (2009) Mining the heterogeneous transformations between data sources to aid record linkage. In: IC-AI, pp 422\u2013428"},{"key":"818_CR27","doi-asserted-by":"crossref","unstructured":"Sarawagi S, Bhamidipaty A (2002) Interactive deduplication using active learning. In: KDD, pp 269\u2013278","DOI":"10.1145\/775047.775087"},{"issue":"1","key":"818_CR28","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.cosrev.2007.05.001","volume":"1","author":"SE Schaeffer","year":"2007","unstructured":"Schaeffer SE (2007) Graph clustering. Comput Sci Rev 1(1):27\u201364","journal-title":"Comput Sci Rev"},{"key":"818_CR29","doi-asserted-by":"crossref","unstructured":"Shen W, DeRose P, Vu L, Doan A, Ramakrishnan R (2007) Source-aware entity matching: a compositional approach. In: ICDE, pp 196\u2013205","DOI":"10.1109\/ICDE.2007.367865"},{"key":"818_CR30","unstructured":"Shen W, Li X, Doan A (2005) Constraint-based entity matching. In: AAAI, pp 862\u2013867"},{"key":"818_CR31","doi-asserted-by":"crossref","unstructured":"Whang SE, Menestrina D, Koutrika G, Theobald M, Garcia-Molina H (2009) Entity resolution with iterative blocking. In: SIGMOD conference, pp 219\u2013232","DOI":"10.1145\/1559845.1559870"},{"key":"818_CR32","doi-asserted-by":"crossref","unstructured":"Xiao C, Wang W, Lin X, Yu JX (2008) Efficient similarity joins for near duplicate detection. In: WWW, pp 131\u2013140","DOI":"10.1145\/1367497.1367516"},{"key":"818_CR33","doi-asserted-by":"crossref","unstructured":"Yang X, Wang B, Li C (2008) Cost-based variable-length-gram selection for string collections to support approximate queries efficiently. In: SIGMOD conference, pp 353\u2013364","DOI":"10.1145\/1376616.1376655"},{"key":"818_CR34","doi-asserted-by":"crossref","unstructured":"Yannakakis M (1978) Node- and edge-deletion np-complete problems. In: STOC, pp 253\u2013264","DOI":"10.1145\/800133.804355"},{"key":"818_CR35","doi-asserted-by":"crossref","unstructured":"Yin X, Han J, Yu PS (2007) Object distinction: distinguishing objects with identical names. In: ICDE, pp 1242\u20131246","DOI":"10.1109\/ICDE.2007.368983"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-015-0818-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-015-0818-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-015-0818-7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,19]],"date-time":"2019-08-19T16:04:32Z","timestamp":1566230672000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-015-0818-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1,14]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,2]]}},"alternative-id":["818"],"URL":"https:\/\/doi.org\/10.1007\/s10115-015-0818-7","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,1,14]]}}}