{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T15:09:18Z","timestamp":1725548958469},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540233053"},{"type":"electronic","value":"9783540301929"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2004]]},"DOI":"10.1007\/978-3-540-30192-9_53","type":"book-chapter","created":{"date-parts":[[2010,3,2]],"date-time":"2010-03-02T18:02:43Z","timestamp":1267552963000},"page":"536-546","source":"Crossref","is-referenced-by-count":13,"title":["Clustering Structured Web Sources: A Schema-Based, Model-Differentiation Approach"],"prefix":"10.1007","author":[{"given":"Bin","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin Chen-Chuan","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"53_CR1","unstructured":"Chang, K.C.C., He, B., Li, C., Zhang, Z.: Structured databases on the web: Observations and implications. Technical Report UIUCDCS-R-2003-2321, Dept. of Computer Science, UIUC (2003)"},{"key":"53_CR2","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/S0306-4379(00)00022-3","volume":"25","author":"S. Guha","year":"2000","unstructured":"Guha, S., Rastogi, R., Shim, K.: ROCK: A robust clustering algorithm for categorical attributes. Information Systems\u00a025, 345\u2013366 (2000)","journal-title":"Information Systems"},{"key":"53_CR3","doi-asserted-by":"crossref","unstructured":"Barbara, D., Li, Y., Couto, J.: Coolcat: An entropy-based algorithm for categorical clustering. In: Proceedings of CIKM Conference (2002)","DOI":"10.1145\/584792.584888"},{"key":"53_CR4","unstructured":"Brunk, H.D.: An introduction to mathematical statistics. Blaisdell Pub. Co. (1965)"},{"key":"53_CR5","doi-asserted-by":"publisher","first-page":"803","DOI":"10.2307\/2532201","volume":"49","author":"J.D. Banfield","year":"1993","unstructured":"Banfield, J.D., Raftery, A.E.: Model-based gaussian and non-gaussian clustering. Biometrics\u00a049, 803\u2013821 (1993)","journal-title":"Biometrics"},{"key":"53_CR6","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1137\/S1064827596311451","volume":"20","author":"C. Fraley","year":"1999","unstructured":"Fraley, C.: Algorithms for model-based Gaussian hierarchical clustering. SIAM Journal on Scientific Computing\u00a020, 270\u2013281 (1999)","journal-title":"SIAM Journal on Scientific Computing"},{"key":"53_CR7","unstructured":"Meila, M., Heckerman, D.: An experimental comparison of several clustering and initialization methods. Technical report, Microsoft Research, MSR-TR-98-06 (1998)"},{"key":"53_CR8","unstructured":"Levy, A.Y., Rajaraman, A., Ordille, J.J.: Querying heterogeneous information sources using source descriptions. In: Proceedings of the VLDB Conference (1996)"},{"key":"53_CR9","unstructured":"Papakonstantinou, Y., Garc\u00eda-Molina, H., Ullman, J.: Medmaker: A mediation system based on declarative specifications. In: Proceedings of the ICDE Conference (1996)"},{"key":"53_CR10","doi-asserted-by":"crossref","unstructured":"Callan, J.P., Connell, M., Du., A.: Automatic discovery of language models for text databases. In: Proceedings of the SIGMOD Conference (1999)","DOI":"10.1145\/304182.304224"},{"key":"53_CR11","doi-asserted-by":"crossref","unstructured":"Ipeirotis, P.G., Luis Gravano, M.S.: Probe, count, and classify: Categorizing hidden web databases. In: Proceedings of the SIGMOD Conference (2001)","DOI":"10.1145\/375663.375671"},{"key":"53_CR12","unstructured":"Meng, W., Liu, K.L., Yu, C.T., Wang, X., Chang, Y., Rishe, N.: Determining text databases to search in the internet. In: Proceedings of the VLDB Conference (1998)"},{"key":"53_CR13","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1007\/s007780050005","volume":"8","author":"D. Gibson","year":"1998","unstructured":"Gibson, D., Kleinberg, J.M., Raghavan, P.: Clustering categorical data: An approach based on dynamical systems. VLDB Journal\u00a08, 222\u2013236 (1998)","journal-title":"VLDB Journal"},{"key":"53_CR14","doi-asserted-by":"crossref","unstructured":"Ganti, V., Gehrke, J., Ramakrishnan, R.: CACTUS \u2013 Clustering categorical data using summaries. In: Proceedings of Knowledge Discovery and Data Mining, pp. 73\u201383 (1999)","DOI":"10.1145\/312129.312201"},{"key":"53_CR15","unstructured":"He, B., Tao, T., Chang, K.C.C.: Clustering structured web sources: A schema-based, model-differentiation approach. Technical Report UIUCDCS-R-2003-2322, Dept. of Computer Science, UIUC (2003)"},{"key":"53_CR16","doi-asserted-by":"crossref","unstructured":"Ponte, J., Croft, W.: A language modelling approach to information retrieval. In: Proceedings of the 21st ACM SIGIR Conference on Research and Development in Information Retrieval (1998)","DOI":"10.1145\/290941.291008"},{"key":"53_CR17","doi-asserted-by":"crossref","unstructured":"He, B., Chang, K.C.C.: Statistical schema matching across web query interfaces. In: Proceedings of the 2003 ACM SIGMOD Conference (2003)","DOI":"10.1145\/872757.872784"},{"key":"53_CR18","doi-asserted-by":"publisher","DOI":"10.1002\/0471249688","volume-title":"Categorical Data Analysis","author":"A. Agresti","year":"2002","unstructured":"Agresti, A.: Categorical Data Analysis. John Wiley & Sons, Inc., New Jersey (2002)"},{"key":"53_CR19","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"A.K. Jain","year":"1999","unstructured":"Jain, A.K., Murty, M.N., Flynn, P.J.: Data clustering: A review. ACM Computing Surveys\u00a031, 264\u2013323 (1999)","journal-title":"ACM Computing Surveys"},{"key":"53_CR20","unstructured":"Berkhin, P.: Survey of clustering data mining techniques. Technical report, Accrue Software (2002)"}],"container-title":["Lecture Notes in Computer Science","Current Trends in Database Technology - EDBT 2004 Workshops"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-30192-9_53.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T04:46:52Z","timestamp":1605761212000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-30192-9_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004]]},"ISBN":["9783540233053","9783540301929"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-30192-9_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2004]]}}}