{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T13:24:20Z","timestamp":1708953860297},"reference-count":57,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2013,8,13]],"date-time":"2013-08-13T00:00:00Z","timestamp":1376352000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2013,10]]},"DOI":"10.1007\/s00778-013-0328-8","type":"journal-article","created":{"date-parts":[[2013,8,12]],"date-time":"2013-08-12T07:46:44Z","timestamp":1376293604000},"page":"711-726","source":"Crossref","is-referenced-by-count":10,"title":["Hybrid entity clustering using crowds and data"],"prefix":"10.1007","volume":"22","author":[{"given":"Jongwuk","family":"Lee","sequence":"first","affiliation":[]},{"given":"Hyunsouk","family":"Cho","sequence":"additional","affiliation":[]},{"given":"Jin-Woo","family":"Park","sequence":"additional","affiliation":[]},{"given":"Young-rok","family":"Cha","sequence":"additional","affiliation":[]},{"given":"Seung-won","family":"Hwang","sequence":"additional","affiliation":[]},{"given":"Zaiqing","family":"Nie","sequence":"additional","affiliation":[]},{"given":"Ji-Rong","family":"Wen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,8,13]]},"reference":[{"key":"328_CR1","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C.: A human-computer cooperative system for effective high dimensional clustering. In: KDD (2001)","DOI":"10.1145\/502512.502542"},{"key":"328_CR2","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C., Wolf, J.L., Yu, P.S., Procopiuc, C., Park, J.S.: Fast algorithms for projected clustering. In: SIGMOD (1999)","DOI":"10.1145\/304182.304188"},{"key":"328_CR3","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C., Yu, P.S.: Finding generalized projected clusters in high dimensional spaces. In: SIGMOD (2000)","DOI":"10.1145\/342009.335383"},{"key":"328_CR4","doi-asserted-by":"crossref","unstructured":"Agrawal, R., Gehrke, J., Gunopulos, D., Raghavan, P.: Automatic subspace clustering of high-dimensional data for a data mining applications. In: SIGMOD (1998)","DOI":"10.1145\/276304.276314"},{"key":"328_CR5","doi-asserted-by":"crossref","unstructured":"Agrawal, R., Gollapudi, S., Halverson, A., Ieong, S.: Diversifying search results. In: WSDM, pp. 5\u201314 (2009)","DOI":"10.1145\/1498759.1498766"},{"key":"328_CR6","doi-asserted-by":"crossref","unstructured":"Ananthakrishna, R., Chaudhuri, S., Ganti, V.: Eliminating fuzzy duplicates in data warehouses. In: VLDB, pp. 586\u2013597 (2002)","DOI":"10.1016\/B978-155860869-6\/50058-5"},{"key":"328_CR7","doi-asserted-by":"crossref","unstructured":"Arasu, A., G\u00f6tz, M., Kaushik, R.: On active learning of record matching packages. In: SIGMOD Conference, pp. 783\u2013794 (2010)","DOI":"10.1145\/1807167.1807252"},{"key":"328_CR8","doi-asserted-by":"crossref","unstructured":"Basu, S., Bilenko, M., Mooney, R.J.: A probabilistic framework for semi-supervised clustering. In: KDD, pp. 59\u201368 (2004)","DOI":"10.1145\/1014052.1014062"},{"issue":"3","key":"328_CR9","first-page":"209","volume":"10","author":"B Bazzanella","year":"2011","unstructured":"Bazzanella, B., Stoermer, H., Bouquet, P.: Entity type disambiguation in user queries. JIKM 10(3), 209\u2013224 (2011)","journal-title":"JIKM"},{"key":"328_CR10","unstructured":"Bilenko, M., Basu, S., Sahami, M.: Adaptive product normalization: Using online learning for recored linkage in comparison shopping. In: ICDM (2005)"},{"key":"328_CR11","doi-asserted-by":"crossref","unstructured":"Bouquet, P., Palpanas, T., Stoermer, H., Vignolo, M.: A conceptual model for a web-scale entity name system. In: ASWC, pp. 46\u201360 (2009)","DOI":"10.1007\/978-3-642-10871-6_4"},{"key":"328_CR12","doi-asserted-by":"crossref","unstructured":"Carterette, B., Chandar, P.: Probabilistic models of ranking novel documents for faceted topic retrieval. In: CIKM, pp. 1287\u20131296 (2009)","DOI":"10.1145\/1645953.1646116"},{"key":"328_CR13","doi-asserted-by":"crossref","unstructured":"Cheng, C.-H., Fu, A.W., Zhang, Y.: Entropy-based subspace clustering for mining numerical data. In: KDD (1999)","DOI":"10.1145\/312129.312199"},{"key":"328_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, D., Kannan, R., Vempala, S., Wang, G.: A divide-merge methodology for clustering. In: TODS (2005)","DOI":"10.1145\/1065167.1065192"},{"key":"328_CR15","doi-asserted-by":"crossref","unstructured":"Chierichetti, F., Kumar, R., Pandey, S., Vassilvitskii, S.: Finding the jaccard median. In: SODA, pp. 293\u2013311 (2010)","DOI":"10.1137\/1.9781611973075.25"},{"key":"328_CR16","doi-asserted-by":"crossref","unstructured":"Cohen, W.W.: Integration of heterogeneous databases without common domains using queries based on textual similarity. In: SIGMOD, pp. 201\u2013212 (1998)","DOI":"10.1145\/276305.276323"},{"key":"328_CR17","doi-asserted-by":"crossref","unstructured":"Cui, Y., Hasler, N., Thorm\u00e4hlen, T., Seidel, H.-P.: Scale invariant feature transform with irregular orientation histogram binning. In: ICIAR, pp. 258\u2013267 (2009)","DOI":"10.1007\/978-3-642-02611-9_26"},{"issue":"4","key":"328_CR18","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1145\/1924421.1924442","volume":"54","author":"A Doan","year":"2011","unstructured":"Doan, A., Ramakrishnan, R., Halevy, A.Y.: Crowdsourcing systems on the world-wide web. Commun. ACM 54(4), 86\u201396 (2011)","journal-title":"Commun. ACM"},{"key":"328_CR19","doi-asserted-by":"crossref","unstructured":"Franklin, M.J., Kossmann, D., Kraska, T., Ramesh, S., Xin, R.: CrowdDB: answering queries with crowdsourcing. In: SIGMOD, pp. 61\u201372 (2011)","DOI":"10.1145\/1989323.1989331"},{"key":"328_CR20","unstructured":"Goil, S., Nagesh, H., Choudhary, A.: Mafia: efficient and scalable subspace clustering for very large data sets. Technical Report, Northwesthen University (1999)"},{"key":"328_CR21","unstructured":"Gomes, R., Welinder, P., Krause, A., Perona, P.: Crowdclustering. In: NIPS, pp. 558\u2013566 (2011)"},{"key":"328_CR22","doi-asserted-by":"crossref","unstructured":"Hearst, M.A., Pedersen, J.O.: Re-examining the cluster hypothesis: Scatter\/Gather on retrieval results. In: SIGIR (1996)","DOI":"10.1145\/243199.243216"},{"key":"328_CR23","doi-asserted-by":"crossref","unstructured":"Jain, A., Pennacchiotti, M.: Open entity extraction from web search query logs. In: COLING, pp. 510\u2013518 (2010)","DOI":"10.1145\/1963192.1963225"},{"key":"328_CR24","unstructured":"Jang, M., Park, J.-W., Hwang, S.: Predictive mining of comparable entities from the web. In: AAAI (2012)"},{"key":"328_CR25","doi-asserted-by":"crossref","unstructured":"Ji, X., Xu, W., Zhu, S.: Document clustering with prior knowledge. In: SIGIR (2006)","DOI":"10.1145\/1148170.1148241"},{"key":"328_CR26","doi-asserted-by":"crossref","unstructured":"Jindal, N., Liu, B.: Identifying comparative sentences in text documents. In: SIGIR, pp. 244\u2013251 (2006)","DOI":"10.1145\/1148170.1148215"},{"key":"328_CR27","doi-asserted-by":"crossref","unstructured":"Lee, J., Hwang, S., Nie, Z., Wen, J.-R.: Query result clustering for object-level search. In: KDD, pp. 1205\u20131214 (2009)","DOI":"10.1145\/1557019.1557149"},{"key":"328_CR28","doi-asserted-by":"crossref","unstructured":"Lee, J., Hwang, S., Nie, Z., Wen, J.-R.: Navigation system for product search. In: ICDE, pp. 1113\u20131116 (2010)","DOI":"10.1109\/ICDE.2010.5447780"},{"issue":"12","key":"328_CR29","first-page":"1295","volume":"4","author":"T Lee","year":"2011","unstructured":"Lee, T., Wang, Z., Wang, H., Hwang, S.: Web scale taxonomy cleansing. PVLDB 4(12), 1295\u20131306 (2011)","journal-title":"PVLDB"},{"key":"328_CR30","unstructured":"Li, S., Lin, C.-Y., Song, Y.-I., Li, Z.: Comparable entity mining from comparative questions. In: ACL, pp. 650\u2013658 (2010)"},{"key":"328_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, W., Lin, Y., Jing, L.: Spectral geometry for simultaneously clustering and ranking query search results. In: SIGIR (2008)","DOI":"10.1145\/1390334.1390427"},{"key":"328_CR32","unstructured":"Marcus, A., Wu, E., Madden, S., Miller, R.C.: Crowdsourced databases: Query processing with people. In: CIDR, pp. 211\u2013214 (2011)"},{"key":"328_CR33","unstructured":"Mecca, G., Raunich, S., Pappalardo, A.: A new algorithm for clustering search results. Data Knowl. Eng. 62(3), 504\u2013522 (2007)"},{"key":"328_CR34","doi-asserted-by":"crossref","unstructured":"Nie, Z., Ma, Y., Shi, S., Wen, J.-R., Ma, W.-Y.: Web object retrieval. In: WWW (2007)","DOI":"10.1145\/1242572.1242584"},{"key":"328_CR35","unstructured":"Nie, Z., Wen, J.-R., Ma, W.-Y.: Object-level vertical search. In: CIDR (2007)"},{"key":"328_CR36","doi-asserted-by":"crossref","unstructured":"Nie, Z., Wen, J.-R., Ma, W.-Y.: Statistical entity extraction from the web. Proc. IEEE 100(9), 2675\u20132687 (2012)","DOI":"10.1109\/JPROC.2012.2191369"},{"key":"328_CR37","doi-asserted-by":"crossref","unstructured":"Nie, Z., Zhang, Y., Wen, J.-R., Ma, W.-Y.: Object-level ranking: bringing order to web objects. In: WWW (2005)","DOI":"10.1145\/1060745.1060828"},{"key":"328_CR38","unstructured":"Parameswaran, A.G., Polyzotis, N.: Answering queries using humans, algorithms and databases. In: CIDR, pp. 160\u2013166 (2011)"},{"issue":"1","key":"328_CR39","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1145\/1007730.1007731","volume":"6","author":"L Parsons","year":"2004","unstructured":"Parsons, L., Haque, E., Liu, H.: Subspace clustering for high dimensional data: a review. SIGKDD Newsletter 6(1), 90\u2013105 (2004)","journal-title":"SIGKDD Newsletter"},{"key":"328_CR40","doi-asserted-by":"crossref","unstructured":"Patrikainen, A., Melia, M.: Comparing subspace clusterings. TKDE 18(7), 902\u2013916 (2006)","DOI":"10.1109\/TKDE.2006.106"},{"key":"328_CR41","doi-asserted-by":"crossref","unstructured":"Radlinski, F., Dumais, S.T.: Improving personalized web search using result diversification. In: SIGIR, pp. 691\u2013692 (2006)","DOI":"10.1145\/1148170.1148320"},{"key":"328_CR42","doi-asserted-by":"crossref","unstructured":"Scripps, J., Tan, P.-N.: Clustering in the presence of bridge-nodes. In: SDM (2006)","DOI":"10.1137\/1.9781611972764.24"},{"key":"328_CR43","doi-asserted-by":"crossref","unstructured":"Selke, J., Lofi, C., Balke, W.-T.: Pushing the boundaries of crowd-enabled databases with query-driven schema expansion. PVLDB 5(6), 538\u2013549 (2012)","DOI":"10.14778\/2168651.2168655"},{"key":"328_CR44","unstructured":"Song, Y., Wang, H., Wang, Z., Li, H., Chen, W.: Short text conceptualization using a probabilistic knowledgebase. In: IJCAI, pp. 2330\u20132336 (2011)"},{"key":"328_CR45","unstructured":"Wagstaff, K., Cardie, C., Rogers, S., Schroedl, S.: Conttrainted k-means clustering with background knowledge. In: ICML (2001)"},{"issue":"11","key":"328_CR46","first-page":"1483","volume":"5","author":"J Wang","year":"2012","unstructured":"Wang, J., Kraska, T., Franklin, M.J., Feng, J.: CrowdER: crowdsourcing entity resolution. PVLDB 5(11), 1483\u20131494 (2012)","journal-title":"PVLDB"},{"key":"328_CR47","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhai, C.: Learn from web search logs to organize search results. In: SIGIR (2007)","DOI":"10.1145\/1277741.1277759"},{"key":"328_CR48","doi-asserted-by":"crossref","unstructured":"Wang, X.-J., Ma, W.-Y., He, Q.-C., Li, X.: Grouping web image search result. In: ACM Multimedia, pp. 436\u2013439 (2004)","DOI":"10.1145\/1027527.1027632"},{"issue":"6","key":"328_CR49","doi-asserted-by":"crossref","first-page":"1261","DOI":"10.1007\/s00778-009-0136-3","volume":"18","author":"SE Whang","year":"2009","unstructured":"Whang, S.E., Benjelloun, O., Garcia-Molina, H.: Generic entity resolution with negative rules. VLDB J. 18(6), 1261\u20131277 (2009)","journal-title":"VLDB J."},{"key":"328_CR50","doi-asserted-by":"crossref","unstructured":"Whang, S.E., Lofgren, P., Garcia-Molina, H.: Question selection for crowd entity resolution. In: PVLDB (2013)","DOI":"10.14778\/2536336.2536337"},{"issue":"4","key":"328_CR51","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.infsof.2003.07.003","volume":"46","author":"K-G Woo","year":"2004","unstructured":"Woo, K.-G., Lee, J.-H., Kim, M.-H., Lee, Y.-J.: FINDIT: a fast intelligent subspace clusteing algorithm using diemsnion voting. Inform. Softw. Technol. 46(4), 255\u2013271 (2004)","journal-title":"Inform. Softw. Technol."},{"key":"328_CR52","doi-asserted-by":"crossref","unstructured":"Xu, W., Liu, X., Gong, Y.: Document clustering based on non-negative matrix factorization. In: SIGIR (2003)","DOI":"10.1145\/860435.860485"},{"issue":"11","key":"328_CR53","first-page":"1387","volume":"16","author":"KY Yip","year":"2004","unstructured":"Yip, K.Y., Cheung, D.W., Ng, M.K.: HARP: A practical projected clustering algorithm. TKDE 16(11), 1387\u20131397 (2004)","journal-title":"TKDE"},{"key":"328_CR54","doi-asserted-by":"crossref","unstructured":"Yip, K.Y., Cheung, D.W., Ng, M.K.: On discovery of extremely low-dimensional clusters using semi-supervised projected clustering. In: ICDE (2005)","DOI":"10.1109\/ICDE.2005.96"},{"key":"328_CR55","doi-asserted-by":"crossref","unstructured":"Zamir, O., Etzioni, O.: Web document clustering: a feasibility demonstration. In: SIGIR (1998)","DOI":"10.1145\/290941.290956"},{"key":"328_CR56","doi-asserted-by":"crossref","unstructured":"Zeng, H.-J., He, Q.-C., Chen, Z., Ma, W.-Y., Ma, J.: Learning to cluster web search results. In: SIGIR (2004)","DOI":"10.1145\/1008992.1009030"},{"key":"328_CR57","unstructured":"Zhu, X., Ghahramani, Z., Lafferty, J.D.: Semi-supervised learning using gaussian fields and harmonic functions. In: ICML, pp. 912\u2013919 (2003)"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-013-0328-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-013-0328-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-013-0328-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,20]],"date-time":"2019-07-20T17:04:09Z","timestamp":1563642249000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-013-0328-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,8,13]]},"references-count":57,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2013,10]]}},"alternative-id":["328"],"URL":"https:\/\/doi.org\/10.1007\/s00778-013-0328-8","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,8,13]]}}}