{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T05:08:23Z","timestamp":1750136903077,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":28,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642312342"},{"type":"electronic","value":"9783642312359"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-31235-9_18","type":"book-chapter","created":{"date-parts":[[2012,6,14]],"date-time":"2012-06-14T12:12:45Z","timestamp":1339675965000},"page":"262-279","source":"Crossref","is-referenced-by-count":10,"title":["Efficient Similarity Search in Very Large String Sets"],"prefix":"10.1007","author":[{"given":"Dandy","family":"Fenz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dustin","family":"Lange","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Astrid","family":"Rheinl\u00e4nder","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Felix","family":"Naumann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulf","family":"Leser","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"18_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1007\/978-3-540-39984-1_25","volume-title":"String Processing and Information Retrieval","author":"S.A. Aghili","year":"2003","unstructured":"Aghili, S.A., Agrawal, D.P., El Abbadi, A.: BFT: Bit Filtration Technique for Approximate String Join in Biological Databases. In: Nascimento, M.A., de Moura, E.S., Oliveira, A.L. (eds.) SPIRE 2003. LNCS, vol.\u00a02857, pp. 326\u2013340. Springer, Heidelberg (2003)"},{"key":"18_CR2","unstructured":"Behm, A., Vernica, R., Alsubaiee, S., Ji, S., Lu, J., Jin, L., Lu, Y., Li, C.: UCI Flamingo Package 4.0 (2011)"},{"key":"18_CR3","unstructured":"Bocek, T., Hunt, E., Stiller, B.: Fast Similarity Search in Large Dictionaries. Technical report, Department of Informatics, University of Zurich (2007)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Celikik, M., Bast, H.: Fast error-tolerant search on very large texts. In: Proc. of the ACM Symposium on Applied Computing (SAC), pp. 1724\u20131731 (2009)","DOI":"10.1145\/1529282.1529669"},{"issue":"1","key":"18_CR5","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1093\/nar\/12.1Part1.175","volume":"12","author":"J.W. Fickett","year":"1984","unstructured":"Fickett, J.W.: Fast optimal alignment. Nucleic Acids Research\u00a012(1), 175\u2013179 (1984)","journal-title":"Nucleic Acids Research"},{"key":"18_CR6","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1145\/367390.367400","volume":"3","author":"E. Fredkin","year":"1960","unstructured":"Fredkin, E.: Trie memory. Commun. of the ACM\u00a03, 490\u2013499 (1960)","journal-title":"Commun. of the ACM"},{"key":"18_CR7","unstructured":"Grahne, G., Zhu, J.: Efficiently using prefix-trees in mining frequent itemsets. In: Proc. of the ICDM Workshop on Frequent Itemset Mining Implementations (2003)"},{"key":"18_CR8","unstructured":"Gravano, L., Ipeirotis, P.G., Jagadish, H.V., Koudas, N., Muthukrishnan, S., Srivastava, D.: Approximate string joins in a database (Almost) for free. In: Proc. of the Intl. Conf. on Very Large Databases (VLDB), pp. 491\u2013500. Morgan Kaufmann (2001)"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Gravano, L., Ipeirotis, P.G., Koudas, N., Srivastava, D.: Text joins in an RDBMS for web data integration. In: Proc. of the Intl. World Wide Web Conf. (WWW), pp. 90\u2013101 (2003)","DOI":"10.1145\/775165.775166"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Gusfield, D.: Algorithms on Strings, Trees and Sequences: Computer Science and Computational Biology. Cambridge University Press (1997)","DOI":"10.1017\/CBO9780511574931"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Han, J., Pei, J., Yin, Y., Mao, R.: Mining frequent patterns without candidate generation: A Frequent-Pattern tree approach. Data Mining and Knowledge Discovery\u00a08(1) (2004)","DOI":"10.1023\/B:DAMI.0000005258.31418.83"},{"key":"18_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1007\/11408079_69","volume-title":"Database Systems for Advanced Applications","author":"R. Jampani","year":"2005","unstructured":"Jampani, R., Pudi, V.: Using Prefix-Trees for Efficiently Computing Set Joins. In: Zhou, L., Ooi, B.-C., Meng, X. (eds.) DASFAA 2005. LNCS, vol.\u00a03453, pp. 761\u2013772. Springer, Heidelberg (2005)"},{"key":"18_CR13","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions and reversals. Soviet Physics Doklady (1966)"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Li, C., Lu, J., Lu, Y.: Efficient merging and filtering algorithms for approximate string searches. In: Proc. of the Intl. Conf. on Data Engineering (ICDE), pp. 257\u2013266. IEEE Computer Society (2008)","DOI":"10.1109\/ICDE.2008.4497434"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, G., Feng, J., Zhou, L.: Effective indices for efficient approximate string search and similarity join. In: Proc. of the Intl. Conf. on Web-Age Information Management, pp. 127\u2013134. IEEE Computer Society (2008)","DOI":"10.1109\/WAIM.2008.17"},{"issue":"4","key":"18_CR16","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1145\/321479.321481","volume":"15","author":"D.R. Morrison","year":"1968","unstructured":"Morrison, D.R.: PATRICIA \u2013 practical algorithm to retrieve information coded in alphanumeric. Journal of the ACM\u00a015(4), 514\u2013534 (1968)","journal-title":"Journal of the ACM"},{"key":"18_CR17","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/BF01185432","volume":"12","author":"E. Myers","year":"1994","unstructured":"Myers, E.: A sublinear algorithm for approximate keyword searching. Algorithmica\u00a012, 345\u2013374 (1994)","journal-title":"Algorithmica"},{"issue":"3","key":"18_CR18","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1145\/316542.316550","volume":"46","author":"G. Myers","year":"1999","unstructured":"Myers, G.: A fast bit-vector algorithm for approximate string matching based on dynamic programming. Journal of the ACM\u00a046(3), 395\u2013415 (1999)","journal-title":"Journal of the ACM"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Navarro, G.: A guided tour to approximate string matching. ACM Computing Surveys\u00a033(1) (2001)","DOI":"10.1145\/375360.375365"},{"key":"18_CR20","first-page":"2001","volume":"24","author":"G. Navarro","year":"2000","unstructured":"Navarro, G., Baeza-Yates, R., Sutinen, E., Tarhio, J.: Indexing methods for approximate string matching. IEEE Data Engineering Bulletin\u00a024, 2001 (2000)","journal-title":"IEEE Data Engineering Bulletin"},{"key":"18_CR21","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1147\/rd.32.0114","volume":"3","author":"M.O. Rabin","year":"1959","unstructured":"Rabin, M.O., Scott, D.: Finite automata and their decision problems. IBM J. Res. Dev.\u00a03, 114\u2013125 (1959)","journal-title":"IBM J. Res. Dev."},{"key":"18_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-3-642-13818-8_36","volume-title":"Scientific and Statistical Database Management","author":"A. Rheinl\u00e4nder","year":"2010","unstructured":"Rheinl\u00e4nder, A., Knobloch, M., Hochmuth, N., Leser, U.: Prefix Tree Indexing for Similarity Search and Similarity Joins on Genomic Data. In: Gertz, M., Lud\u00e4scher, B. (eds.) SSDBM 2010. LNCS, vol.\u00a06187, pp. 519\u2013536. Springer, Heidelberg (2010)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Rheinl\u00e4nder, A., Leser, U.: Scalable sequence similarity search in main memory on multicores. In: International Workshop on High Performance in Bioinformatics and Biomedicine, HiBB (2011)","DOI":"10.1007\/978-3-642-29740-3_3"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Sahinalp, S.C., Tasan, M., Macker, J., Ozsoyoglu, Z.M.: Distance based indexing for string proximity search. In: Proc. of the Intl. Conf. on Data Engineering (ICDE), pp. 125\u2013136 (2003)","DOI":"10.1109\/ICDE.2003.1260787"},{"key":"18_CR25","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1109\/69.536247","volume":"8","author":"H. Shang","year":"1996","unstructured":"Shang, H., Merrett, T.: Tries for approximate string matching. IEEE Transactions on Knowledge and Data Engineering (TKDE)\u00a08, 540\u2013547 (1996)","journal-title":"IEEE Transactions on Knowledge and Data Engineering (TKDE)"},{"key":"18_CR26","first-page":"52","volume":"4","author":"T.K. Vintsyuk","year":"1968","unstructured":"Vintsyuk, T.K.: Speech discrimination by dynamic programming. Cybernetics and Systems Analysis\u00a04, 52\u201357 (1968)","journal-title":"Cybernetics and Systems Analysis"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Wang, W., Xiao, C., Lin, X., Zhang, C.: Efficient approximate entity extraction with edit distance constraints. In: Proc. of the ACM Intl. Conf. on Management of Data (SIGMOD), pp. 759\u2013770 (2009)","DOI":"10.1145\/1559845.1559925"},{"key":"18_CR28","doi-asserted-by":"crossref","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. of the VLDB Endowment\u00a01, 933\u2013944 (2008)","journal-title":"Proc. of the VLDB Endowment"}],"container-title":["Lecture Notes in Computer Science","Scientific and Statistical Database Management"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-31235-9_18.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T10:11:28Z","timestamp":1743415888000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-31235-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642312342","9783642312359"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-31235-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}