{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:40:17Z","timestamp":1743072017423,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642201516"},{"type":"electronic","value":"9783642201523"}],"license":[{"start":{"date-parts":[[2011,1,1]],"date-time":"2011-01-01T00:00:00Z","timestamp":1293840000000},"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":[[2011]]},"DOI":"10.1007\/978-3-642-20152-3_3","type":"book-chapter","created":{"date-parts":[[2011,4,8]],"date-time":"2011-04-08T22:42:08Z","timestamp":1302302528000},"page":"31-46","source":"Crossref","is-referenced-by-count":4,"title":["PG-Skip: Proximity Graph Based Clustering of Long Strings"],"prefix":"10.1007","author":[{"given":"Michail","family":"Kazimianec","sequence":"first","affiliation":[]},{"given":"Nikolaus","family":"Augsten","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"unstructured":"Mazeika, A., B\u00f6hlen, M.H.: Cleansing databases of misspelled proper nouns. In: CleanDB (2006)","key":"3_CR1"},{"key":"3_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/978-3-642-15576-5_23","volume-title":"Advances in Databases and Information Systems","author":"M. Kazimianec","year":"2010","unstructured":"Kazimianec, M., Augsten, N.: Exact and efficient proximity graph computation. In: Catania, B., Ivanovi\u0107, M., Thalheim, B. (eds.) ADBIS 2010. LNCS, vol.\u00a06295, pp. 293\u2013307. Springer, Heidelberg (2010)"},{"doi-asserted-by":"crossref","unstructured":"Sarawagi, S., Kirpal, A.: Efficient set joins on similarity predicates. In: SIGMOD Conference, pp. 743\u2013754 (2004)","key":"3_CR3","DOI":"10.1145\/1007568.1007652"},{"key":"3_CR4","first-page":"814","volume-title":"International Conference on Data Engineering (ICDE)","author":"N. Augsten","year":"2008","unstructured":"Augsten, N., B\u00f6hlen, M., Dyreson, C., Gamper, J.: Approximate joins for data-centric XML. In: International Conference on Data Engineering (ICDE), Canc\u00fan, Mexico, pp. 814\u2013823. IEEE Computer Society, Los Alamitos (2008)"},{"key":"3_CR5","first-page":"257","volume-title":"International Conference on Data Engineering (ICDE)","author":"C. Li","year":"2008","unstructured":"Li, C., Lu, J., Lu, Y.: Efficient merging and filtering algorithms for approximate string searches. In: International Conference on Data Engineering (ICDE), Washington, DC, USA, pp. 257\u2013266. IEEE Computer Society, Los Alamitos (2008)"},{"doi-asserted-by":"crossref","unstructured":"Kazimianec, M., Mazeika, A.: Clustering of short strings in large databases. In: International Workshop on Database and Expert Systems Applications, pp. 368\u2013372 (2009)","key":"3_CR6","DOI":"10.1109\/DEXA.2009.73"},{"unstructured":"Li, C., Wang, B., Yang, X.: Vgram: improving performance of approximate queries on string collections using variable-length grams. In: Proceedings of the 33rd International Conference on Very Large Data Bases, VLDB 2007, pp. 303\u2013314, VLDB Endowment (2007)","key":"3_CR7"},{"key":"3_CR8","first-page":"281","volume-title":"Proc. of the fifth Berkeley Symposium on Mathematical Statistics and Probability","author":"J.B. MacQueen","year":"1967","unstructured":"MacQueen, J.B.: Some methods for classification and analysis of multivariate observations. In: Cam, L.M.L., Neyman, J. (eds.) Proc. of the fifth Berkeley Symposium on Mathematical Statistics and Probability, vol.\u00a01, pp. 281\u2013297. University of California Press, Berkeley (1967)"},{"key":"3_CR9","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316801","volume-title":"Finding Groups in Data An Introduction to Cluster Analysis","author":"L. Kaufman","year":"1990","unstructured":"Kaufman, L., Rousseeuw, P.: Finding Groups in Data An Introduction to Cluster Analysis. Wiley Interscience, New York (1990)"},{"unstructured":"Ester, M., Kriegel, H.-P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD, pp. 226\u2013231 (1996)","key":"3_CR10"},{"issue":"2","key":"3_CR11","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1145\/304181.304187","volume":"28","author":"M. Ankerst","year":"1999","unstructured":"Ankerst, M., Breunig, M.M., Kriegel, H.-P., Sander, J.: Optics: Ordering points to identify the clustering structure. ACM SIGMOD Record\u00a028(2), 49\u201360 (1999)","journal-title":"ACM SIGMOD Record"},{"issue":"4","key":"3_CR12","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1145\/146370.146380","volume":"24","author":"K. Kukich","year":"1992","unstructured":"Kukich, K.: Techniques for automatically correcting words in text. ACM Comput. Surv.\u00a024(4), 377\u2013439 (1992)","journal-title":"ACM Comput. Surv."},{"issue":"5","key":"3_CR13","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1109\/TKDE.2003.1232265","volume":"15","author":"V.J. Hodge","year":"2003","unstructured":"Hodge, V.J., Austin, J.: A comparison of standard spell checking algorithms and a novel binary neural approach. IEEE Trans. on Knowl. and Data Eng.\u00a015(5), 1073\u20131081 (2003)","journal-title":"IEEE Trans. on Knowl. and Data Eng."},{"doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Ganjam, K., Ganti, V., Motwani, R.: Robust and efficient fuzzy match for online data cleaning. In: SIGMOD, pp. 313\u2013324 (2003)","key":"3_CR14","DOI":"10.1145\/872757.872796"},{"unstructured":"Arasu, A., Ganti, V., Kaushik, R.: Efficient exact set-similarity joins. In: VLDB 2006: Proceedings of the 32nd International Conference on Very Large Data Bases, pp. 918\u2013929, VLDB Endowment (2006)","key":"3_CR15"},{"issue":"1","key":"3_CR16","doi-asserted-by":"publisher","first-page":"933","DOI":"10.14778\/1453856.1453957","volume":"1","author":"C. Xiao","year":"2008","unstructured":"Xiao, C., Wang, W., Lin, X.: Ed-join: an efficient algorithm for similarity joins with edit distance constraints. Proc. VLDB Endow.\u00a01(1), 933\u2013944 (2008)","journal-title":"Proc. VLDB Endow."}],"container-title":["Lecture Notes in Computer Science","Database Systems for Advanced Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-20152-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,6]],"date-time":"2024-04-06T00:56:22Z","timestamp":1712364982000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-20152-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642201516","9783642201523"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-20152-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2011]]}}}