{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T20:18:59Z","timestamp":1725567539235},"publisher-location":"Berlin, Heidelberg","reference-count":10,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642163203"},{"type":"electronic","value":"9783642163210"}],"license":[{"start":{"date-parts":[[2010,1,1]],"date-time":"2010-01-01T00:00:00Z","timestamp":1262304000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-16321-0_32","type":"book-chapter","created":{"date-parts":[[2010,10,5]],"date-time":"2010-10-05T14:51:32Z","timestamp":1286290292000},"page":"303-308","source":"Crossref","is-referenced-by-count":5,"title":["Hypergeometric Language Model and Zipf-Like Scoring Function for Web Document Similarity Retrieval"],"prefix":"10.1007","author":[{"given":"Felipe","family":"Bravo-Marquez","sequence":"first","affiliation":[]},{"given":"Gaston","family":"L\u2019Huillier","sequence":"additional","affiliation":[]},{"given":"Sebasti\u00e1n A.","family":"R\u00edos","sequence":"additional","affiliation":[]},{"given":"Juan D.","family":"Vel\u00e1squez","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"32_CR1","volume-title":"Modern Information Retrieval","author":"R.A. Baeza-Yates","year":"1999","unstructured":"Baeza-Yates, R.A., Ribeiro-Neto, B.: Modern Information Retrieval. Addison-Wesley Longman Publishing Co., Inc., Boston (1999)"},{"issue":"3","key":"32_CR2","doi-asserted-by":"publisher","first-page":"938","DOI":"10.1214\/aoms\/1177700066","volume":"36","author":"W.L. Hakerness","year":"1965","unstructured":"Hakerness, W.L.: Properties of the extended hypergeometric distribution. Ann. Math. Statist.\u00a036(3), 938\u2013945 (1965)","journal-title":"Ann. Math. Statist."},{"key":"32_CR3","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1145\/1148170.1148222","volume-title":"SIGIR 2006: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","author":"M. Henzinger","year":"2006","unstructured":"Henzinger, M.: Finding near-duplicate web pages: a large-scale evaluation of algorithms. In: SIGIR 2006: Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 284\u2013291. ACM, New York (2006)"},{"issue":"4","key":"32_CR4","first-page":"247","volume":"2","author":"A.R. Pereira Jr.","year":"2004","unstructured":"Pereira Jr., A.R., Ziviani, N.: Retrieving similar documents from the web. J. Web Eng.\u00a02(4), 247\u2013261 (2004)","journal-title":"J. Web Eng."},{"key":"32_CR5","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"C.D. Manning","year":"2008","unstructured":"Manning, C.D., Raghavan, P., Sch\u00fctze, H.: Introduction to Information Retrieval. Cambridge University Press, New York (2008)"},{"key":"32_CR6","unstructured":"Nagaraj, S.V.: Web Caching And Its Applications. Kluwer International Series in Engineering and Computer Science. Kluwer Academic Publishers, Norwell (2004)"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Selberg, E., Etzioni, O.: The metacrawler architecture for resource aggregation on the web. IEEE Expert, 11\u201314 (January\u2013February 1997)","DOI":"10.1109\/64.577468"},{"key":"32_CR8","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1145\/860575.860706","volume-title":"AAMAS 2003: Proceedings of the second international joint conference on Autonomous agents and multiagent systems","author":"G.L. Somlo","year":"2003","unstructured":"Somlo, G.L., Howe, A.E.: Using web helper agent profiles in query generation. In: AAMAS 2003: Proceedings of the second international joint conference on Autonomous agents and multiagent systems, pp. 812\u2013818. ACM, New York (2003)"},{"issue":"5","key":"32_CR9","first-page":"1391","volume":"25","author":"B. Zaka","year":"2009","unstructured":"Zaka, B.: Empowering plagiarism detection with a web services enabled collaborative network. Journal of Information Science and Engineering\u00a025(5), 1391\u20131403 (2009)","journal-title":"Journal of Information Science and Engineering"},{"key":"32_CR10","volume-title":"Human Behavior and the Principle of Least Effort","author":"G.K. Zipf","year":"1949","unstructured":"Zipf, G.K.: Human Behavior and the Principle of Least Effort. Addison-Wesley, Reading (1949)"}],"container-title":["Lecture Notes in Computer Science","String Processing and Information Retrieval"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-16321-0_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,5]],"date-time":"2019-06-05T07:13:40Z","timestamp":1559718820000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-16321-0_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642163203","9783642163210"],"references-count":10,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-16321-0_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}