{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:04:34Z","timestamp":1767985474764,"version":"3.49.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,1,23]],"date-time":"2015-01-23T00:00:00Z","timestamp":1421971200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2016,1]]},"DOI":"10.1007\/s10115-015-0820-0","type":"journal-article","created":{"date-parts":[[2015,1,23]],"date-time":"2015-01-23T16:57:54Z","timestamp":1422032274000},"page":"185-212","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Clustering XML documents by patterns"],"prefix":"10.1007","volume":"46","author":[{"given":"Maciej","family":"Piernik","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dariusz","family":"Brzezinski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tadeusz","family":"Morzy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,1,23]]},"reference":[{"key":"820_CR1","doi-asserted-by":"crossref","unstructured":"Aggarwal CC, Ta N, Wang J, Feng J, Zaki MJ (2007) XProj: a framework for projected structural clustering of xml documents. In: Proceedings of the 13th ACM SIGKDD international conference on knowledge discovery and data mining, pp 46\u201355","DOI":"10.1145\/1281192.1281201"},{"issue":"4","key":"820_CR2","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1145\/1978802.1978804","volume":"43","author":"A Algergawy","year":"2011","unstructured":"Algergawy A, Mesiti M, Nayak R, Saake G (2011) Xml data clustering: an overview. ACM Comput Surv 43(4):25\u201341","journal-title":"ACM Comput Surv"},{"key":"820_CR3","doi-asserted-by":"crossref","unstructured":"Barbosa D, Mendelzon AO, Keenleyside J, Lyons KA (2002) Toxgene: a template-based data generator for XML. In: Proceedings of the 2002 ACM SIGMOD international conference on management of data, p 616","DOI":"10.1145\/564691.564769"},{"issue":"4","key":"820_CR4","doi-asserted-by":"crossref","first-page":"1407","DOI":"10.1109\/18.681318","volume":"44","author":"CH Bennett","year":"1998","unstructured":"Bennett CH, G\u00e1cs P, Li M, Vit\u00e1nyi PMB, Zurek WH (1998) Information distance. IEEE Trans Inf Theory 44(4):1407\u20131423","journal-title":"IEEE Trans Inf Theory"},{"key":"820_CR5","unstructured":"Bray T, Paoli J, Sperberg-McQueen C (1998) Extensible markup language (XML) 1.0. Recommendation, World Wide Web Consortium (W3C). http:\/\/www.w3.org\/TR\/1998\/REC-xml-19980210"},{"issue":"3","key":"820_CR6","first-page":"877","volume":"40","author":"D Brzezinski","year":"2011","unstructured":"Brzezinski D, Lesniewska A, Morzy T, Piernik M (2011) XCleaner: a new method for clustering xml documents by structure. Control Cybern 40(3):877\u2013891","journal-title":"Control Cybern"},{"key":"820_CR7","unstructured":"Buttler D (2004) A short survey of document structure similarity algorithms. In: Proceedings of the international conference on internet computing, IC \u201904, pp 3\u20139"},{"key":"820_CR8","unstructured":"Candillier L, Tellier I, Torre F (2005) Transforming XML trees for efficient classification and clustering. In: Proceeding of the 4th international workshop of the initiative for the evaluation of XML retrieval, INEX 2005, pp 469\u2013480"},{"issue":"2","key":"820_CR9","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1109\/TKDE.2005.30","volume":"17","author":"Y Chi","year":"2005","unstructured":"Chi Y, Xia Y, Yang Y, Muntz RR (2005) Mining closed and maximal frequent subtrees from databases of labeled rooted trees. IEEE Trans Knowl Data Eng 17(2):190\u2013202","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"820_CR10","doi-asserted-by":"crossref","unstructured":"Dalamagas T, Cheng T, Winkel KJ, Sellis TK (2004) Clustering XML documents by structure. In: 3rd Helenic conference on methods and applications of artificial intelligence AI, SETN, LNCS, vol 3025, pp 112\u2013121","DOI":"10.1007\/978-3-540-24674-9_13"},{"key":"820_CR11","first-page":"1","volume":"7","author":"J Demsar","year":"2006","unstructured":"Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1\u201330","journal-title":"J Mach Learn Res"},{"key":"820_CR12","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1145\/1273221.1273230","volume":"41","author":"L Denoyer","year":"2007","unstructured":"Denoyer L, Gallinari P (2007) Report on the XML mining track at INEX 2005 and INEX 2006: categorization and clustering of XML documents. SIGIR Forum 41:79\u201390","journal-title":"SIGIR Forum"},{"issue":"6","key":"820_CR13","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1136\/jamia.2001.0080552","volume":"8","author":"RH Dolin","year":"2001","unstructured":"Dolin RH, Alschuler L, Beebe C, Biron PV, Boyer SL, Essin D, Kimber E, Lincoln T, Mattison JE (2001) The HL7 clinical document architecture. J Am Med Inform Assoc 8(6):552\u2013569","journal-title":"J Am Med Inform Assoc"},{"key":"820_CR14","unstructured":"Doucet A, Ahonen-Myka H (2002) Na\u00efve clustering of a large XML document collection. In: Proceedings of the 1st workshop of the initiative for the evaluation of XML retrieval (INEX), pp 81\u201387"},{"key":"820_CR15","unstructured":"Fayyad UM, Piatetsky-Shapiro G, Smyth P (1996) From data mining to knowledge discovery: an overview. In: Advances in knowledge discovery and data mining, AAAI, pp 1\u201334"},{"key":"820_CR16","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/7287.001.0001","volume-title":"WordNet: an electronic Lexical database","author":"C Fellbaum","year":"1998","unstructured":"Fellbaum C (1998) WordNet: an electronic Lexical database. Bradford Books, Cambridge"},{"key":"820_CR17","unstructured":"Flesca S, Manco G, Masciari E, Pontieri L, Pugliese A (2002) Detecting structural similarities between XML documents. In: WebDB, pp 55\u201360"},{"key":"820_CR18","doi-asserted-by":"crossref","unstructured":"Hagenbuchner M, Sperduti A, Tsoi AC, Trentini F, Scarselli F, Gori M (2005a) Clustering XML documents using self-organizing maps for structures. In: Proceeding of the 4th international workshop of the initiative for the evaluation of XML retrieval, INEX 2005, pp 481\u2013496","DOI":"10.1007\/978-3-540-34963-1_37"},{"key":"820_CR19","doi-asserted-by":"crossref","unstructured":"Hagenbuchner M, Sperduti A, Tsoi AC, Trentini F, Scarselli F, Gori M (2005b) Clustering XML documents using self-organizing maps for structures. In: Workshop of the initiative for the evaluation of XML retrieval","DOI":"10.1007\/978-3-540-34963-1_37"},{"issue":"2","key":"820_CR20","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MIS.2009.36","volume":"24","author":"AY Halevy","year":"2009","unstructured":"Halevy AY, Norvig P, Pereira F (2009) The unreasonable effectiveness of data. IEEE Intell Syst 24(2):8\u201312","journal-title":"IEEE Intell Syst"},{"key":"820_CR21","unstructured":"Helmer S (2007) Measuring the structural similarity of semistructured documents using entropy. In: Proceedings of the 33rd international conference on very large data bases, pp 1022\u20131032"},{"key":"820_CR22","volume-title":"Self-organizing maps. Springer series in information science","author":"T Kohonen","year":"2000","unstructured":"Kohonen T (2000) Self-organizing maps. Springer series in information science, 3rd edn. Springer, Berlin","edition":"3"},{"key":"820_CR23","unstructured":"Kurgan LA, Swiercz W, Cios KJ (2002) Semantic mapping of XML tags using inductive machine learning. In: Proceedings of the 2002 international conference on machine learning and applications, pp 99\u2013109"},{"key":"820_CR24","doi-asserted-by":"crossref","unstructured":"Lee ML, Yang LH, Hsu W, Yang X (2002) XClust: clustering XML schemas for effective integration. In: Proceedings of the 2002 ACM CIKM international conference on information and knowledge management, pp 292\u2013299","DOI":"10.1145\/584792.584841"},{"key":"820_CR25","unstructured":"Lesniewska A (2009) Clustering XML documents by structure. In: Associated workshops and doctoral consortium of the 13th east European conference, pp 238\u2013246"},{"key":"820_CR26","doi-asserted-by":"crossref","unstructured":"Leung HP, Chung KFL, fai Chan SC, Luk RWP (2005) XML document clustering using common XPath. In: 2005 International workshop on challenges in web information retrieval and integration (WIRI 2005), pp 91\u201396","DOI":"10.1109\/WIRI.2005.39"},{"issue":"1","key":"820_CR27","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/TKDE.2004.1264824","volume":"16","author":"W Lian","year":"2004","unstructured":"Lian W, Cheung DWL, Mamoulis N, Yiu SM (2004) An efficient and scalable algorithm for clustering XML documents by structure. IEEE Trans Knowl Data Eng 16(1):82\u201396","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"820_CR28","doi-asserted-by":"crossref","unstructured":"Nayak R, Iryadi W (2006) XMine: a methodology for mining XML structure. In: Proceedings of the 8th Asia-Pacific web conference, pp 786\u2013792","DOI":"10.1007\/11610113_74"},{"key":"820_CR29","unstructured":"Nayak R, Xu S (2005) XML documents clustering by structures. In: Proceeding of the 4th international workshop of the initiative for the evaluation of XML retrieval, INEX 2005, pp 432\u2013442"},{"key":"820_CR30","unstructured":"Nierman A, Jagadish HV (2002) Evaluating structural similarity in XML documents. In: WebDB, pp 61\u201366"},{"issue":"4","key":"820_CR31","first-page":"334","volume":"5","author":"M Pawlik","year":"2011","unstructured":"Pawlik M, Augsten N (2011) RTED: a robust algorithm for the tree edit distance. PVLDB 5(4):334\u2013345","journal-title":"PVLDB"},{"key":"820_CR32","doi-asserted-by":"crossref","unstructured":"Piernik M, Brzezinski D, Morzy T, Lesniewska A (2014) XML clustering: a review of structural approaches. Knowl Eng Rev. doi: 10.1017\/S0269888914000216","DOI":"10.1017\/S0269888914000216"},{"key":"820_CR33","volume-title":"Introduction to modern information retrieval","author":"G Salton","year":"1984","unstructured":"Salton G, McGill M (1984) Introduction to modern information retrieval. McGraw-Hill Book Company, New York"},{"issue":"11","key":"820_CR34","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1145\/361219.361220","volume":"18","author":"G Salton","year":"1975","unstructured":"Salton G, Wong A, Yang CS (1975) A vector space model for automatic indexing. Commun ACM 18(11):613\u2013620","journal-title":"Commun ACM"},{"key":"820_CR35","doi-asserted-by":"crossref","unstructured":"Shen Y, Wang B (2003) Clustering schemaless XML documents. In: Proceedings of CoopIS, DOA, and ODBASE 2003, LNCS, vol 2888, pp 767\u2013784","DOI":"10.1007\/978-3-540-39964-3_49"},{"key":"820_CR36","unstructured":"SIGMOD (2011) http:\/\/www.sigmod.org\/publications\/sigmod-record\/xml-edition"},{"key":"820_CR37","doi-asserted-by":"crossref","unstructured":"Tagarelli A, Greco S (2006) Toward semantic XML clustering. In: Proceedings of the 6th SIAM international conference on data mining, pp 188\u2013199","DOI":"10.1137\/1.9781611972764.17"},{"issue":"3","key":"820_CR38","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 (2009) An overview on XML similarity: background, current trends and future directions. Comput Sci Rev 3(3):151\u2013173","journal-title":"Comput Sci Rev"},{"key":"820_CR39","unstructured":"Vercoustre AM, Fegas M, Gul S, Lechevallier Y (2005) A flexible structured-based representation for XML document mining. In: Proceeding of the 4th international workshop of the initiative for the evaluation of XML retrieval, INEX 2005, pp 443\u2013457"},{"key":"820_CR40","unstructured":"W3C (2001) Mathematical markup language (MathML) Version 2.0. W3C Recommendation"},{"key":"820_CR41","unstructured":"W3C (2007) SOAP specifications. http:\/\/www.w3.org\/TR\/soap"},{"issue":"7","key":"820_CR42","doi-asserted-by":"crossref","first-page":"988","DOI":"10.1093\/bioinformatics\/bti082","volume":"21","author":"J Westbrook","year":"2005","unstructured":"Westbrook J, Ito N, Nakamura H, Henrick K, Berman HM (2005) PDBML: the representation of archival macromolecular structure data in XML. Bioinformatics 21(7):988\u2013992","journal-title":"Bioinformatics"},{"key":"820_CR43","doi-asserted-by":"crossref","unstructured":"Yang G (2004) The complexity of mining maximal frequent itemsets and maximal frequent patterns. In: Proceedings of the 10th ACM SIGKDD international conference on knowledge discovery and data mining, pp 344\u2013353","DOI":"10.1145\/1014052.1014091"},{"issue":"1","key":"820_CR44","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1007\/s10115-008-0138-2","volume":"19","author":"J Yang","year":"2009","unstructured":"Yang J, Cheung WKW, Chen X (2009) Learning element similarity matrix for semi-structured document analysis. Knowl Inf Syst 19(1):53\u201378","journal-title":"Knowl Inf Syst"},{"key":"820_CR45","doi-asserted-by":"crossref","unstructured":"Yoon JP, Raghavan V, Chakilam V (2001) BitCube: A three-dimensional bitmap indexing for XML documents. In: Proceedings of the 13th international conference on scientific and statistical database management, pp 158\u2013167","DOI":"10.1109\/SSDM.2001.938548"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-015-0820-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-015-0820-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-015-0820-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,20]],"date-time":"2019-08-20T01:45:44Z","timestamp":1566265544000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-015-0820-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1,23]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,1]]}},"alternative-id":["820"],"URL":"https:\/\/doi.org\/10.1007\/s10115-015-0820-0","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,1,23]]}}}