{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:57:11Z","timestamp":1740171431752,"version":"3.37.3"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Data Semant"],"published-print":{"date-parts":[[2018,6]]},"DOI":"10.1007\/s13740-018-0088-0","type":"journal-article","created":{"date-parts":[[2018,6,2]],"date-time":"2018-06-02T08:24:36Z","timestamp":1527927876000},"page":"87-105","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Approximating the Schema of a Set of Documents by Means of Resemblance"],"prefix":"10.1007","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3223-2186","authenticated-orcid":false,"given":"Alberto","family":"Abell\u00f3","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xavier","family":"de Palol","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohand-Sa\u00efd","family":"Hacid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,2]]},"reference":[{"key":"88_CR1","doi-asserted-by":"crossref","unstructured":"Abiteboul S (1997) Querying semi-structured data. In: Proceedings of 6th international conference on database theory (ICDT\u201997), LNCS, vol 1186. Springer, pp 1\u201318","DOI":"10.1007\/3-540-62222-5_33"},{"issue":"1","key":"88_CR2","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/S0306-4379(03)00031-0","volume":"29","author":"E Bertino","year":"2004","unstructured":"Bertino E, Guerrini G, Mesiti M (2004) A matching algorithm for measuring the structural similarity between an XML document and a DTD and its applications. Inf Syst 29(1):23\u201346","journal-title":"Inf Syst"},{"key":"88_CR3","volume-title":"Data on the Web\u2013from relations to semistructured data and XML","author":"S Abiteboul","year":"2000","unstructured":"Abiteboul S, Buneman P, Suciu D (2000) Data on the Web\u2013from relations to semistructured data and XML. Morgan Kaufmann, Burlington"},{"issue":"9","key":"88_CR4","doi-asserted-by":"publisher","first-page":"922","DOI":"10.14778\/2777598.2777601","volume":"8","author":"L Wang","year":"2015","unstructured":"Wang L, Hassanzadeh O, Zhang S, Shi J, Jiao L, Zou J, Wang C (2015) Schema management for document stores. Proc VLDB Endow 8(9):922\u2013933","journal-title":"Proc VLDB Endow"},{"key":"88_CR5","unstructured":"W3C, Extensible Markup Language (XML) 1.0, 3rd Edition (February 2004)"},{"issue":"1\u20132","key":"88_CR6","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/S0304-3975(00)00294-2","volume":"267","author":"J Albert","year":"2001","unstructured":"Albert J, Giammarresi D, Wood D (2001) Normal form algorithms for extended context-free grammars. Theor Comput Sci 267(1\u20132):35\u201347","journal-title":"Theor Comput Sci"},{"issue":"1","key":"88_CR7","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1023\/A:1021560618289","volume":"7","author":"M Garofalakis","year":"2003","unstructured":"Garofalakis M, Gionis A, Rastogi R, Sechadri S, Shim K (2003) XTRACT: learning document type descriptors from XML document collections. Data Min Knowl Discov 7(1):23\u201356","journal-title":"Data Min Knowl Discov"},{"key":"88_CR8","doi-asserted-by":"crossref","unstructured":"Nestorov S, Abiteboul S, Motwani R (1998) Extracting schema from semistructured data. In: Proceedings of the ACM SIGMOD international conference on management of data (SIGMOD 1998). ACM, pp 295\u2013306","DOI":"10.1145\/276304.276331"},{"key":"88_CR9","doi-asserted-by":"crossref","unstructured":"Sanz I, P\u00e9rez J, Berlanga R, Aramburu M (2003) XML schemata inference and evolution. In: Proceedings of 14th international conference on databases and expert systems applications (DEXA\u201903), LNCS, vol 2736. Springer, pp 109\u2013118","DOI":"10.1007\/978-3-540-45227-0_12"},{"issue":"4","key":"88_CR10","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1016\/j.knosys.2006.08.006","volume":"20","author":"R Nayak","year":"2007","unstructured":"Nayak R, Iryadi W (2007) XML schema clustering with semantic and hierarchical similarity measures. Knowl Based Syst 20(4):336\u2013349","journal-title":"Knowl Based Syst"},{"issue":"3","key":"88_CR11","first-page":"44","volume":"22","author":"J Widom","year":"1999","unstructured":"Widom J (1999) Data management for XML: research directions. IEEE Data Eng Bull 22(3):44\u201352","journal-title":"IEEE Data Eng Bull"},{"key":"88_CR12","doi-asserted-by":"publisher","first-page":"56","DOI":"10.4018\/978-1-59904-228-2.ch003","volume-title":"Emerging techniques and technologies: web data management practices","author":"G Guerrini","year":"2007","unstructured":"Guerrini G, Mesiti M, Sanz I (2007) An overview of similarity measures for clustering XML documents. In: Akali A, Pallis G (eds) Emerging techniques and technologies: web data management practices. IGI Global, Hershey, pp 56\u201378"},{"key":"88_CR13","unstructured":"Wang K, Liu H (1997) Schema discovery for semistructured data. In: 3rd International conference on knowledge discovery and data mining (KDD-97), pp 271\u2013274"},{"key":"88_CR14","doi-asserted-by":"crossref","unstructured":"Hegewald J, Naumann F, Weis M (2006) XStruct: efficient schema extraction from multiple and large XML documents. In: Proceedings of the 22nd international conference on data engineering workshops, ICDE 2006, 3\u20137 Apr 2006, Atlanta, p 81","DOI":"10.1109\/ICDEW.2006.166"},{"key":"88_CR15","unstructured":"Jung J-S, Oh D-I, Kong Y-H, Ahn J-K (2002) Extracting information from XML documents by reverse generating a DTD. In: Proceedings of the EurAsia-ICT 2002, LNCS, vol 2510. Springer, pp 314\u2013321"},{"issue":"4","key":"88_CR16","doi-asserted-by":"publisher","first-page":"14:1","DOI":"10.1145\/1841909.1841911","volume":"4","author":"GJ Bex","year":"2010","unstructured":"Bex GJ, Gelade W, Neven F, Vansummeren S (2010) Learning deterministic regular expressions for the inference of schemas from XML data. ACM Trans Web 4(4):14:1\u201314:32","journal-title":"ACM Trans Web"},{"key":"88_CR17","unstructured":"Moh D-H, Lim E-P, Ng W-K (2000) Re-engineering structures from Web documents. In: 5th ACM conference on digital libraries (DL 2000). ACM, pp 67\u201376"},{"key":"88_CR18","unstructured":"Moh D-H, Lim E-P, Ng W-K (2000) DTD-miner: a tool for mining DTD from XML documents. In: Second international workshop on advance issues of E-commerce and web-based information systems (WECWIS 2000). IEEE Computer Society, pp 144\u2013151"},{"issue":"4","key":"88_CR19","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s11086-005-0032-6","volume":"31","author":"AV Leonov","year":"2005","unstructured":"Leonov AV, Khusnutdinov RR (2005) Study and development of the DTD generation system for XML documents. Program Comput Softw 31(4):197\u2013210","journal-title":"Program Comput Softw"},{"key":"88_CR20","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/S0020-0190(02)00345-9","volume":"85","author":"J-K Min","year":"2003","unstructured":"Min J-K, Ahn J-Y, Cung C-W (2003) Efficient extraction of schemas for XML documents. Inform Process Lett 85:7\u201312","journal-title":"Inform Process Lett"},{"key":"88_CR21","doi-asserted-by":"crossref","unstructured":"Izquierdo JLC, Cabot J (July 8-12, 2013) Discovering implicit schemas in JSON data. In: Web engineering\u201413th international conference, ICWE 2013, Aalborg, Proceedings, 2013, pp 68\u201383","DOI":"10.1007\/978-3-642-39200-9_8"},{"key":"88_CR22","doi-asserted-by":"crossref","unstructured":"Boobna U, de Rougemont M (2004) Correctors for XML data. In: Proceedings of 2nd international XML database symposium (XSYM\u201904), LNCS, vol 3186. Springer, pp 97\u2013111","DOI":"10.1007\/978-3-540-30081-6_8"},{"key":"88_CR23","doi-asserted-by":"publisher","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 (2006) A methodology for clustering XML documents by structure. Inform Syst 31:187\u2013228","journal-title":"Inform Syst"},{"issue":"6","key":"88_CR24","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1137\/0218082","volume":"18","author":"Z Zhang","year":"1989","unstructured":"Zhang Z, Shasha D (1989) Simple fast algorithms for the editing distance between trees and related problems. SIAM J Comput 18(6):1245\u20131262","journal-title":"SIAM J Comput"},{"key":"88_CR25","unstructured":"Klettke M, St\u00f6rl U, Scherzinger S (2015) Schema extraction and structural outlier detection for JSON-based NOSQL data stores. In: Datenbanksysteme f\u00fcr Business, Technologie und Web (BTW), 16. Fachtagung des GI-Fachbereichs \"Datenbanken und Informationssysteme\" (DBIS), 4.-6.3.2015 in Hamburg, Proceedings, pp 425\u2013444"},{"issue":"1","key":"88_CR26","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/BF01202268","volume":"12","author":"V Batagelj","year":"1995","unstructured":"Batagelj V, Bren M (1995) Comparing resemblance measures. J Classif 12(1):73\u201390","journal-title":"J Classif"},{"issue":"1","key":"88_CR27","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/TKDE.2004.1264824","volume":"16","author":"W Lian","year":"2004","unstructured":"Lian W, Cheung D, Mamoulis N, Yiu S-M (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":"88_CR28","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.is.2018.02.007","volume":"75","author":"E Gallinucci","year":"2018","unstructured":"Gallinucci E, Golfarelli M, Rizzi S (2018) Schema profiling of document-oriented databases. Inform Syst 75:13\u201325","journal-title":"Inform Syst"},{"volume-title":"The description logic handbook","year":"2003","key":"88_CR29","unstructured":"Baader F, Calvanese D, McGuinness D, Nardi D, Patel-Schneider P (eds) (2003) The description logic handbook. Cambridge University Press, Cambridge"},{"key":"88_CR30","doi-asserted-by":"crossref","unstructured":"Teege G (1994) Making the difference: a substraction operation for description logics. In: Proceedings of the international conference on principles of knowledge representation and reasoning (KR\u201994). Morgan Kaufmann, pp 540\u2013550","DOI":"10.1016\/B978-1-4832-1452-8.50145-7"},{"key":"88_CR31","doi-asserted-by":"crossref","unstructured":"Estivill-Castro V, Yang J (2000) Fast and robust general purpose clustering algorithms. In: Proceedings of 6th Pacific Rim international conference on artificial intelligence (PRICAI 2000), LNCS, vol 1886. Springer, pp 208\u2013218","DOI":"10.1007\/3-540-44533-1_24"}],"container-title":["Journal on Data Semantics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13740-018-0088-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13740-018-0088-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13740-018-0088-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,2]],"date-time":"2019-06-02T01:45:27Z","timestamp":1559439927000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13740-018-0088-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2018,6]]}},"alternative-id":["88"],"URL":"https:\/\/doi.org\/10.1007\/s13740-018-0088-0","relation":{},"ISSN":["1861-2032","1861-2040"],"issn-type":[{"type":"print","value":"1861-2032"},{"type":"electronic","value":"1861-2040"}],"subject":[],"published":{"date-parts":[[2018,6]]},"assertion":[{"value":"28 April 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}