{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T16:03:00Z","timestamp":1774195380513,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642152504","type":"print"},{"value":"9783642152511","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-15251-1_33","type":"book-chapter","created":{"date-parts":[[2010,8,12]],"date-time":"2010-08-12T14:55:45Z","timestamp":1281624945000},"page":"422-436","source":"Crossref","is-referenced-by-count":12,"title":["An Efficient Similarity Join Algorithm with Cosine Similarity Predicate"],"prefix":"10.1007","author":[{"given":"Dongjoo","family":"Lee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaehui","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junho","family":"Shim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sang-goo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"33_CR1","unstructured":"Chaudhuri, S., Chen, B.C., Ganti, V., Kaushik, R.: Example-driven design of efficient record matching queries. In: VLDB (2007)"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganti, V., Kaushik, R.: A primitive operator for similarity joins in data cleaning. In: ICDE (2006)","DOI":"10.1109\/ICDE.2006.9"},{"key":"33_CR3","doi-asserted-by":"crossref","unstructured":"Henzinger, M.: Finding near-duplicate web pages: a large-scale evaluation of algorithms. In: SIGIR (2006)","DOI":"10.1145\/1148170.1148222"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Bayardo, R.J., Ma, Y., Srikant, R.: Scaling up all pairs similarity search. In: WWW (2007)","DOI":"10.1145\/1242572.1242591"},{"key":"33_CR5","doi-asserted-by":"crossref","unstructured":"Chien, S., Immorlica, N.: Semantic similarity between search engine queries using temporal correlation. In: WWW (2005)","DOI":"10.1145\/1060745.1060752"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Chandel, A., Hassanzadeh, O., Koudas, N., Sadoghi, M., Srivastava, D.: Benchmarking declarative approximate selection predicates. In: SIGMOD (2007)","DOI":"10.1145\/1247480.1247521"},{"issue":"4","key":"33_CR7","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1145\/1095872.1095873","volume":"23","author":"S.L. Chuang","year":"2005","unstructured":"Chuang, S.L., Chien, L.F.: Taxonomy generation for text segments: A practical web-based approach. ACM Trans. Inf. Syst.\u00a023(4), 363\u2013396 (2005)","journal-title":"ACM Trans. Inf. Syst."},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Sahami, M., Heilman, T.D.: A web-based kernel function for measuring the similarity of short text snippets. In: WWW (2006)","DOI":"10.1145\/1135777.1135834"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Spertus, E., Sahami, M., Buyukkokten, O.: Evaluating similarity measures: a large-scale study in the orkut social network. In: KDD (2005)","DOI":"10.1145\/1081870.1081956"},{"key":"33_CR10","doi-asserted-by":"crossref","unstructured":"Xiao, C., Wang, W., Lin, X., Yu, J.X.: Efficient similarity joins for near duplicate detection. In: WWW (2008)","DOI":"10.1145\/1367497.1367516"},{"key":"33_CR11","unstructured":"Arasu, A., Ganti, V., Kaushik, R.: Efficient exact set-similarity joins. In: VLDB (2006)"},{"key":"33_CR12","doi-asserted-by":"crossref","unstructured":"Sarawagi, S., Kirpal, A.: Efficient set joins on similarity predicates. In: SIGMOD (2004)","DOI":"10.1145\/1007568.1007652"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"Xiao, C., Wang, W., Lin, X.: Ed-join: an efficient algorithm for similarity joins with edit distance constraints. In: VLDB (2008)","DOI":"10.14778\/1453856.1453957"},{"key":"33_CR14","unstructured":"Jones, K.S.: A statistical interpretation of term specificity and its application in retrieval. Taylor Graham Series in Foundations of Information Science, pp. 132\u2013142 (1988)"},{"key":"33_CR15","unstructured":"Helmer, S., Moerkotte, G.: Evaluation of main memory join algorithms for joins with set comparison join predicates. In: VLDB (1997)"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Mamoulis, N.: Efficient processing of joins on set-valued attributes. In: SIGMOD (2003)","DOI":"10.1145\/872757.872778"},{"key":"33_CR17","unstructured":"Ramasamy, K., Patel, J.M., Naughton, J.F., Kaushik, R.: Set containment joins: The good, the bad and the ugly. In: VLDB (2000)"},{"issue":"2","key":"33_CR18","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1145\/376284.375714","volume":"30","author":"C. B\u00f6hm","year":"2001","unstructured":"B\u00f6hm, C., Braunm\u00fcller, B., Krebs, F., Kriegel, H.P.: Epsilon grid order: an algorithm for the similarity join on massive high-dimensional data. SIGMOD Rec.\u00a030(2), 379\u2013388 (2001)","journal-title":"SIGMOD Rec."},{"issue":"1","key":"33_CR19","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1023\/A:1011472308196","volume":"4","author":"W. Hersh","year":"2001","unstructured":"Hersh, W.: Managing gigabytes\u2014compressing and indexing documents and images (second edition). Inf. Retr.\u00a04(1), 79\u201380 (2001)","journal-title":"Inf. Retr."},{"key":"33_CR20","unstructured":"Gionis, A., Indyk, P., Motwani, R.: Similarity search in high dimensions via hashing. In: VLDB (1999)"}],"container-title":["Lecture Notes in Computer Science","Database and Expert Systems Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-15251-1_33.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T03:04:02Z","timestamp":1606187042000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-15251-1_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642152504","9783642152511"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-15251-1_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010]]}}}