{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T19:22:42Z","timestamp":1695151362696},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2011,9,22]],"date-time":"2011-09-22T00:00:00Z","timestamp":1316649600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["The VLDB Journal"],"published-print":{"date-parts":[[2012,8]]},"DOI":"10.1007\/s00778-011-0254-6","type":"journal-article","created":{"date-parts":[[2011,9,21]],"date-time":"2011-09-21T09:55:29Z","timestamp":1316598929000},"page":"463-488","source":"Crossref","is-referenced-by-count":12,"title":["Windowed pq-grams for approximate joins of data-centric XML"],"prefix":"10.1007","volume":"21","author":[{"given":"Nikolaus","family":"Augsten","sequence":"first","affiliation":[]},{"given":"Michael","family":"B\u00f6hlen","sequence":"additional","affiliation":[]},{"given":"Curtis","family":"Dyreson","sequence":"additional","affiliation":[]},{"given":"Johann","family":"Gamper","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2011,9,22]]},"reference":[{"key":"254_CR1","doi-asserted-by":"crossref","unstructured":"Cob\u00e9na, G., Abiteboul, S., Marian, A.: Detecting changes in XML documents. In Proceedings of the International Conference on Data Engineering (ICDE), pp. 41\u201352. San Jose, California (2002)","DOI":"10.1109\/ICDE.2002.994696"},{"key":"254_CR2","doi-asserted-by":"crossref","unstructured":"Guha, S., Jagadish, H.V., Koudas, N., Srivastava, D., Ting Y.: Approximate XML joins. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 287\u2013298. Madison, Wisconsin (2002)","DOI":"10.1145\/564724.564725"},{"issue":"8","key":"254_CR3","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1109\/TKDE.2004.19","volume":"16","author":"K.-H. Lee","year":"2004","unstructured":"Lee K.-H., Choy Y.-C., Cho S.-B.: An efficient algorithm to compute differences between structured documents. IEEE Trans. Knowl. Data Eng. (TKDE) 16(8), 965\u2013979 (2004)","journal-title":"IEEE Trans. Knowl. Data Eng. (TKDE)"},{"issue":"3","key":"254_CR4","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1016\/0020-0190(92)90136-J","volume":"42","author":"K. Zhang","year":"1992","unstructured":"Zhang K., Statman R., Shasha D.: On the editing distance between unordered labeled trees. Inf. Process. Lett. 42(3), 133\u2013139 (1992)","journal-title":"Inf. Process. Lett."},{"key":"254_CR5","doi-asserted-by":"crossref","unstructured":"Duszynski, S., Knodel, J., Naab, M., Hein, D., Schitter, C.: Variant comparison\u2014a technique for visualizing software variants. In Working Conference on Reverse Engineering, pp. 229\u2013233. Antwerp, Belgium (2008)","DOI":"10.1109\/WCRE.2008.22"},{"key":"254_CR6","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1093\/nar\/gkh473","volume":"32","author":"K.F. Aoki","year":"2004","unstructured":"Aoki K.F., Yamaguchi A., Ueda N., Akutsu T., Mamitsuka H., Goto S., Kanehisa M.: KCaM (KEGG carbohydrate matcher): a software tool for analyzing the structures of carbohydrate sugar chains. Nucleic Acids Res. 32, 267\u2013272 (2004)","journal-title":"Nucleic Acids Res."},{"issue":"6","key":"254_CR7","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1089\/cmb.2006.13.1165","volume":"13","author":"Y. Horesh","year":"2006","unstructured":"Horesh Y., Mehr R., Unger R.: Designing an A* algorithm for calculating edit distance between rooted-unordered trees. J. Comput. Biol. 13(6), 1165\u20131176 (2006)","journal-title":"J. Comput. Biol."},{"key":"254_CR8","doi-asserted-by":"crossref","unstructured":"Chawathe, S.S., Garcia-Molina, H.: Meaningful change detection in structured data. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 26\u201337. Tucson, Arizona, United States (1997)","DOI":"10.1145\/253260.253266"},{"issue":"3","key":"254_CR9","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1145\/322139.322143","volume":"26","author":"K.-C. Tai","year":"1979","unstructured":"Tai K.-C.: The tree-to-tree correction problem. J. ACM (JACM) 26(3), 422\u2013433 (1979)","journal-title":"J. ACM (JACM)"},{"issue":"2","key":"254_CR10","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1006\/jagm.2001.1170","volume":"40","author":"W. Chen","year":"2001","unstructured":"Chen W.: New algorithm for ordered tree-to-tree correction problem. J. Algorithms 40(2), 135\u2013158 (2001)","journal-title":"J. Algorithms"},{"key":"254_CR11","doi-asserted-by":"crossref","unstructured":"Demaine, E.D., Mozes, S., Rossman, B., Weimann, O.: An optimal decomposition algorithm for tree edit distance. In Proceedings of the 34th International Colloquium on Automata, Languages and Programming (ICALP 2007), vol. 4596 of LNCS, pp. 146\u2013157. Wroclaw, Poland (2007)","DOI":"10.1007\/978-3-540-73420-8_15"},{"key":"254_CR12","doi-asserted-by":"crossref","unstructured":"Klein, P.N.: Computing the edit-distance between unrooted ordered trees. In Proceedings of the 6th European Symposium on Algorithms, vol. 1461 of LNCS, pp. 91\u2013102. Venice, Italy (1998)","DOI":"10.1007\/3-540-68530-8_8"},{"issue":"6","key":"254_CR13","doi-asserted-by":"crossref","first-page":"1245","DOI":"10.1137\/0218082","volume":"18","author":"K. Zhang","year":"1989","unstructured":"Zhang K., Shasha D.: Simple fast algorithms for the editing distance between trees and related problems. SIAM J. Comput. 18(6), 1245\u20131262 (1989)","journal-title":"SIAM J. Comput."},{"issue":"1","key":"254_CR14","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1145\/1061318.1061326","volume":"30","author":"M. Garofalakis","year":"2005","unstructured":"Garofalakis M., Kumar A.: XML stream processing using tree-edit distance embeddings. ACM Trans. Database Syst. (TODS) 30(1), 279\u2013332 (2005)","journal-title":"ACM Trans. Database Syst. (TODS)"},{"key":"254_CR15","unstructured":"Augsten, N., B\u00f6hlen, M., Gamper, J.: Approximate matching of hierarchical data using pq-grams. In Proceedings of the International Conference on Very Large Databases (VLDB), pp. 301\u2013312. Trondheim, Norway (2005)"},{"key":"254_CR16","doi-asserted-by":"crossref","unstructured":"Augsten, N., B\u00f6hlen, M., Gamper, J.: The pq-gram distance between ordered labeled trees. ACM Trans. Database Syst. (TODS) 35(1), (2010)","DOI":"10.1145\/1670243.1670247"},{"key":"254_CR17","doi-asserted-by":"crossref","unstructured":"Ribeiro, L., H\u00e4rder, T.: Evaluating performance and quality of XML-based similarity joins. In Advances in Databases and Information Systems (ADBIS), vol. 5207 of LNCS, pp. 246\u2013261. Pori, Finland (2008)","DOI":"10.1007\/978-3-540-85713-6_18"},{"key":"254_CR18","doi-asserted-by":"crossref","unstructured":"Augsten, N., B\u00f6hlen, M., Dyreson, C., Gamper, J.: Approximate joins for data-centric XML. In Proceedings of the International Conference on Data Engineering (ICDE), pp. 814\u2013823. Canc\u00fan, Mexico (2008)","DOI":"10.1109\/ICDE.2008.4497490"},{"key":"254_CR19","doi-asserted-by":"crossref","unstructured":"Ribeiro, L.A., H\u00e4rder, T., Pimenta, F.S.: A cluster-based approach to XML similarity joins. In Proceedings of the International Database Engineering and Applications Symposium (IDEAS), pp. 182\u2013193. Cetraro, Calabria, Italy (2009)","DOI":"10.1145\/1620432.1620451"},{"issue":"1","key":"254_CR20","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/0304-3975(92)90143-4","volume":"92","author":"E. Ukkonen","year":"1992","unstructured":"Ukkonen E.: Approximate string-matching with q-grams and maximal matches. Theor. Comput. Sci. 92(1), 191\u2013211 (1992)","journal-title":"Theor. Comput. Sci."},{"key":"254_CR21","doi-asserted-by":"crossref","unstructured":"Tatikonda, S., Parthasarathy, S.: Hashing tree-structured data: methods and applications. In Proceedings of the International Conference on Data Engineering (ICDE), pp. 429\u2013440. Long Beach, CA, USA (2010)","DOI":"10.1109\/ICDE.2010.5447882"},{"issue":"3","key":"254_CR22","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1016\/j.cosrev.2009.03.001","volume":"3","author":"J. Tekli","year":"2009","unstructured":"Tekli J., Chbeir R., Y\u00e9tongnon K.: An overview on XML similarity: background, current trends and future directions. Comput. Sci. Rev. 3(3), 151\u2013173 (2009)","journal-title":"Comput. Sci. Rev."},{"key":"254_CR23","doi-asserted-by":"crossref","unstructured":"Amer-Yahia, S., Lakshmanan, L.V.S., Pandit, S.: FleXPath: flexible structure and full-text querying for XML. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 83\u201394 (2004)","DOI":"10.1145\/1007568.1007581"},{"key":"254_CR24","unstructured":"Buttler, D.: A short survey of document structure similarity algorithms. In Proceedings of the International Conference on Internet Computing, pp. 3\u20139. Las Vegas, Nevada, USA (2004)"},{"key":"254_CR25","doi-asserted-by":"crossref","unstructured":"Kriegel, H.-P., Sch\u00f6nauer, S.: Similarity search in structured data. In Data Warehousing and Knowledge Discovery (DaWaK), pp. 309\u2013319 (2003)","DOI":"10.1007\/978-3-540-45228-7_31"},{"key":"254_CR26","doi-asserted-by":"crossref","unstructured":"Chawathe, S.S., Rajaraman, A., Garcia-Molina, H., Widom, J.: Change detection in hierarchically structured information. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 493\u2013504. Montreal, Canada (1996)","DOI":"10.1145\/235968.233366"},{"key":"254_CR27","unstructured":"Wang, Y., DeWitt, D.J., Cai, J.-y.: X-Diff: an effective change detection algorithm for XML documents. In Proceedings of the International Conference on Data Engineering (ICDE), pp. 519\u2013530. Bangalore, India (2003)"},{"key":"254_CR28","doi-asserted-by":"crossref","unstructured":"Weis, M., Naumann, F.: DogmatiX tracks down duplicates in XML. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 431\u2013442. Baltimore, Maryland, USA (2005)","DOI":"10.1145\/1066157.1066207"},{"key":"254_CR29","doi-asserted-by":"crossref","unstructured":"Puhlmann, S., Weis, M., Naumann, F.: XML duplicate detection using sorted neighborhoods. In Proceedings of the International Conference on Extending Database Technology (EDBT), vol. 3896 of LNCS, pp. 773\u2013791. Munich, Germany (2006)","DOI":"10.1007\/11687238_46"},{"issue":"1","key":"254_CR30","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.datak.2007.05.008","volume":"64","author":"I. Sanz","year":"2008","unstructured":"Sanz I., Mesiti M., Guerrini G., Berlanga R.: Fragment-based approximate retrieval in highly heterogeneous XML collections. Data Knowl. Eng. 64(1), 266\u2013293 (2008)","journal-title":"Data Knowl. Eng."},{"key":"254_CR31","doi-asserted-by":"crossref","unstructured":"Bruno, N., Koudas, N., Srivastava, D.: Holistic twig joins: optimal XML pattern matching. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 310\u2013321. Madison, Wisconsin (2002)","DOI":"10.1145\/564691.564727"},{"key":"254_CR32","doi-asserted-by":"crossref","unstructured":"Jiang, H., Wang, W., Lu, H., Yu, J.X.: Holistic twig joins on indexed XML documents. In Proceedings of the International Conference on Very Large Databases (VLDB), pp. 273\u2013284. Berlin, Germany (2003)","DOI":"10.1016\/B978-012722442-8\/50032-X"},{"issue":"3","key":"254_CR33","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.is.2004.11.009","volume":"31","author":"T. Dalamagas","year":"2006","unstructured":"Dalamagas T., Cheng T., Winkel K.-J., Sellis T.: A methodology for clustering XML documents by structure. Inf. Syst. 31(3), 187\u2013228 (2006)","journal-title":"Inf. Syst."},{"issue":"2","key":"254_CR34","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1109\/TKDE.2005.27","volume":"17","author":"S. Flesca","year":"2005","unstructured":"Flesca S., Manco G., Masciari E., Pontieri L., Pugliese A.: Fast detection of XML structural similarity. IEEE Trans. Knowl. Data Eng. (TKDE) 17(2), 160\u2013175 (2005)","journal-title":"IEEE Trans. Knowl. Data Eng. (TKDE)"},{"key":"254_CR35","unstructured":"Helmer, S.: Measuring the structural similarity of semistructured documents using entropy. In Proceedings of the International Conference on Very Large Databases (VLDB), pp. 1022\u20131032. Vienna, Austria (2007)"},{"key":"254_CR36","unstructured":"Nierman, A., Jagadish, H.V.: Evaluating structural similarity in XML documents. In Proceedings of the Fifth International Workshop on the Web and Databases (WebDB 2002), pp. 61\u201366. Madison, Wisconsin, USA (2002)"},{"key":"254_CR37","doi-asserted-by":"crossref","unstructured":"Yang, R., Kalnis, P., Tung, A.K.H.: Similarity evaluation on tree-structured data. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 754\u2013765. Baltimore, Maryland, USA (2005)","DOI":"10.1145\/1066157.1066243"},{"key":"254_CR38","doi-asserted-by":"crossref","unstructured":"Garofalakis, M., Kumar, A.: Correlating XML data streams using tree-edit distance embeddings. In Proceedings of the Twenty-Second ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems (PODS 2003), pp. 143\u2013154. San Diego, California (2003)","DOI":"10.1145\/773153.773168"},{"key":"254_CR39","unstructured":"Rijsbergen, C.J. van: Information Retrieval, 2nd edn. Butterworth-Heinemann (1979)"},{"key":"254_CR40","doi-asserted-by":"crossref","unstructured":"Zezula, P., Amato, G., Dohnal, V., Batko, M.: Similarity Search\u2014The Metric Space Approach, vol. 32 of Advances in Database Systems. Springer-Verlag New York, Inc., Secaucus, NJ, USA (2006)","DOI":"10.1007\/0-387-29151-2"},{"key":"254_CR41","unstructured":"Yianilos, P.N.: Normalized forms for two common metrics. Technical report, NEC Research Institute, 1991 (2002)"},{"issue":"2","key":"254_CR42","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1147\/rd.312.0249","volume":"31","author":"R.M. Karp","year":"1987","unstructured":"Karp R.M., Rabin M.O.: Efficient randomized pattern-matching algorithms. IBM J. Res. Dev. 31(2), 249\u2013260 (1987)","journal-title":"IBM J. Res. Dev."},{"key":"254_CR43","doi-asserted-by":"crossref","unstructured":"Sarawagi, S., Kirpal, A.: Efficient set joins on similarity predicates. In Proceedings of the ACM SIGMOD International Conference on Management of Data, pp. 743\u2013754 (2004)","DOI":"10.1145\/1007568.1007652"},{"key":"254_CR44","unstructured":"Augsten, N., B\u00f6hlen, M., Gamper, J.: An incrementally maintainable index for approximate lookups in hierarchical data. In Proceedings of the International Conference on Very Large Databases (VLDB), pp. 247\u2013258, Seoul, Korea (2006)"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-011-0254-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-011-0254-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-011-0254-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,16]],"date-time":"2019-06-16T00:20:07Z","timestamp":1560644407000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-011-0254-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,9,22]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2012,8]]}},"alternative-id":["254"],"URL":"https:\/\/doi.org\/10.1007\/s00778-011-0254-6","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,9,22]]}}}