{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T20:38:24Z","timestamp":1775767104106,"version":"3.50.1"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2012,2,8]],"date-time":"2012-02-08T00:00:00Z","timestamp":1328659200000},"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":[[2012,10]]},"DOI":"10.1007\/s00778-012-0263-0","type":"journal-article","created":{"date-parts":[[2012,2,7]],"date-time":"2012-02-07T06:28:06Z","timestamp":1328596086000},"page":"677-702","source":"Crossref","is-referenced-by-count":12,"title":["Measuring structural similarity of semistructured data based on information-theoretic approaches"],"prefix":"10.1007","volume":"21","author":[{"given":"Sven","family":"Helmer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaus","family":"Augsten","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"B\u00f6hlen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,2,8]]},"reference":[{"key":"263_CR1","doi-asserted-by":"crossref","unstructured":"Arasu, A., Garcia-Molina, H.: Extracting structured data from web pages. In: ACM SIGMOD International Conference on Management of Data, pp. 337\u2013348 (2003)","DOI":"10.1145\/872757.872799"},{"issue":"1","key":"263_CR2","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1037\/0033-295X.95.1.124","volume":"95","author":"F.G. Ashby","year":"1988","unstructured":"Ashby F.G., Perrin N.A.: Toward a unified theory of similarity and recognition. Psychol. Rev. 95(1), 124\u2013150 (1988)","journal-title":"Psychol. Rev."},{"key":"263_CR3","unstructured":"Augsten, N., B\u00f6hlen, M.H., Gamper, J.: Approximate matching of hierarchical data using pq-grams. In: Proceedings of the 31st International Conference on Very Large Data Bases (VLDB\u201905), pp. 301\u2013312, Trondheim (2005)"},{"key":"263_CR4","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. IEEE Computer Society (2008)","DOI":"10.1109\/ICDE.2008.4497490"},{"key":"263_CR5","doi-asserted-by":"crossref","unstructured":"Augsten, N., Barbosa, D., B\u00f6hlen, M., Palpanas, T.: TASM: Top-k approximate subtree matching. In: Proceedings of the International Conference on Data Engineering (ICDE), pp. 353\u2013364, Long Beach, California, USA. IEEE Computer Society (2010)","DOI":"10.1109\/ICDE.2010.5447905"},{"key":"263_CR6","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":"263_CR7","volume-title":"Modern Information Retrieval","author":"R.A. Baeza-Yates","year":"1999","unstructured":"Baeza-Yates R.A., Ribeiro-Neto B.A.: Modern Information Retrieval. Addison-Wesley, Reading (1999)"},{"issue":"4","key":"263_CR8","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1007\/s11280-005-1544-y","volume":"8","author":"D. Barbosa","year":"2005","unstructured":"Barbosa D., Mignet L., Veltri P.: Studying the XML Web: gathering statistics from an XML sample. World Wide Web J. 8(4), 413\u2013438 (2005)","journal-title":"World Wide Web J."},{"key":"263_CR9","unstructured":"Baumgartner, R., Flesca, S., Gottlob, G.: Visual web information extraction with Lixto. In: International Conference on Very Large Databases (VLDB\u201901), pp. 119\u2013128 (2001)"},{"issue":"4","key":"263_CR10","doi-asserted-by":"crossref","first-page":"1407","DOI":"10.1109\/18.681318","volume":"44","author":"C.H. Bennet","year":"1998","unstructured":"Bennet C.H., G\u00e1cs P., Li M., Vit\u00e1nyi P.M.B.: Zurek W.H.: Information distance. IEEE Trans. Inf. Theory 44(4), 1407\u20131423 (1998)","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"1","key":"263_CR11","doi-asserted-by":"crossref","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.: A matching algorithm for measuring the structural similarity between an XML document and a DTD and its applications. Inf. Syst. 29(1), 23\u201346 (2004)","journal-title":"Inf. Syst."},{"key":"263_CR12","doi-asserted-by":"crossref","unstructured":"Bohrer, K., Liu, X., McLaughlin, S., Schonberg, E., Singh, M.: Object oriented XML query by example. In: ER (Workshops), pp. 323\u2013329 (2003)","DOI":"10.1007\/978-3-540-39597-3_32"},{"key":"263_CR13","unstructured":"Buttler, D.: A short survey of document structure similarity algorithms. In: 5th International Conference on Internet Computing, Las Vegas, Nevada (2004)"},{"key":"263_CR14","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1145\/321356.321363","volume":"13","author":"G.J. Chaitin","year":"1966","unstructured":"Chaitin G.J.: On the length of programs for computing finite binary sequences. J. ACM 13, 547\u2013569 (1966)","journal-title":"J. ACM"},{"key":"263_CR15","doi-asserted-by":"crossref","unstructured":"Chawathe, S., Garcia-Molina, H.: Meaningful change detection in structured data. In: ACM SIGMOD International Conference on Management of Data, pp. 26\u201337 (1997)","DOI":"10.1145\/253260.253266"},{"key":"263_CR16","doi-asserted-by":"crossref","unstructured":"Chawathe, S., Rajaraman, A., Garcia-Molina, H., Widom, J.: Change detection in hierarchically structured information. In: ACM SIGMOD International Conference on Management of Data, pp. 493\u2013504 (1996)","DOI":"10.1145\/235968.233366"},{"key":"263_CR17","doi-asserted-by":"crossref","unstructured":"Cherukuri, V.S., Candan, K.S.: Propagation-vectors for trees (PVT): concise yet effective summaries for hierarchical data and trees. In: ACM Workshop on Large-Scale Distributed Systems for Information Retrieval (LSDS-IR), Napa Valley, CA (2008)","DOI":"10.1145\/1458469.1458481"},{"issue":"4","key":"263_CR18","doi-asserted-by":"crossref","first-page":"1523","DOI":"10.1109\/TIT.2005.844059","volume":"51","author":"R. Cilibrasi","year":"2005","unstructured":"Cilibrasi R., Vit\u00e1nyi P.M.B.: Clustering by compression. IEEE Trans. Inf. Theory 51(4), 1523\u2013 (2005)","journal-title":"IEEE Trans. Inf. Theory"},{"key":"263_CR19","doi-asserted-by":"crossref","unstructured":"Coutinho, D.P., Figueiredo, M.A.T.: Information theoretic text classification using the Ziv-Merhav method. In: Proceeding 2nd Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA), pp. 355\u2013362, Estoril, Portugal (2005)","DOI":"10.1007\/11492542_44"},{"key":"263_CR20","volume-title":"Elements of Information Theory","author":"T.M. Cover","year":"2006","unstructured":"Cover T.M., Thomas J.A.: Elements of Information Theory. Wiley, London (2006)"},{"key":"263_CR21","doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: RoadRunner: towards automatic data extraction from large web sites. In: International Conference on Very Large Databases (VLDB\u201901), pp. 109\u2013118 (2001)","DOI":"10.1145\/564691.564778"},{"issue":"3","key":"263_CR22","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."},{"key":"263_CR23","doi-asserted-by":"crossref","unstructured":"de Castro Reis, D., Golgher, P.B., da Silva, A.S., Laender, A.H.F.: Automatic web news extraction using tree edit distance. In: 13th International World Wide Web Conference (WWW\u201904), Manhattan, New York (2004)","DOI":"10.1145\/988672.988740"},{"issue":"3","key":"263_CR24","doi-asserted-by":"crossref","first-page":"297","DOI":"10.2307\/1932409","volume":"26","author":"L.R. Dice","year":"1945","unstructured":"Dice L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297\u2013302 (1945)","journal-title":"Ecology"},{"issue":"2","key":"263_CR25","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. 17(2), 160\u2013175 (2005)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"263_CR26","doi-asserted-by":"crossref","unstructured":"Garofalakis, M.N., Gionis, A., Rastogi, R., Seshadri, S., Shim, K.: XTRACT: a system for extracting document type descriptors from XML documents. In: ACM SIGMOD International Conference on Management of Data, pp. 165\u2013176 (2000)","DOI":"10.1145\/342009.335409"},{"key":"263_CR27","unstructured":"Gr\u00fcnwald, P., Vit\u00e1nyi, P.M.B.: Shannon information and Kolmogorov complexity. The Computing Research Repository (CoRR), cs.IT\/0410002 (2004)"},{"key":"263_CR28","unstructured":"Helmer, S.: Measuring the structural similarity of semistructured documents using entropy. In: Proceedings of the 33rd International Conference on Very Large Data Bases (VLDB\u201907), pp. 1022\u20131032, Vienna (2007)"},{"issue":"1","key":"263_CR29","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1504\/IJIQ.2007.013376","volume":"1","author":"K.G. Herbert","year":"2007","unstructured":"Herbert K.G., Wang J.T.L.: Biological data cleaning: a case study. Int. J. Inf. Qual. 1(1), 60\u201382 (2007)","journal-title":"Int. J. Inf. Qual."},{"key":"263_CR30","volume-title":"Mathematical Taxonomy","author":"N. Jardine","year":"1971","unstructured":"Jardine N., Sibson R.: Mathematical Taxonomy. Wiley, New York (1971)"},{"key":"263_CR31","doi-asserted-by":"crossref","unstructured":"Kim, J.W., Candan, K.S.: CP\/CV: concept similarity mining without frequency information from domain describing taxonomies. In: ACM International Conference on Information and Knowledge Management (CIKM), pp. 483\u2013492, Arlington, Virginia (2006)","DOI":"10.1145\/1183614.1183684"},{"key":"263_CR32","volume-title":"The Art of Computer Programming, Volume I: Fundamental Algorithms","author":"D. Knuth","year":"1973","unstructured":"Knuth D.: The Art of Computer Programming, Volume I: Fundamental Algorithms. Addison-Wesley, Reading (1973)"},{"key":"263_CR33","first-page":"1","volume":"1","author":"A.N. Kolmogorov","year":"1965","unstructured":"Kolmogorov A.N.: Three approaches to the quantitative definition of information. Probl. Inf. Transm. 1, 1\u20137 (1965)","journal-title":"Probl. Inf. Transm."},{"key":"263_CR34","volume-title":"Information Theory and Statistics","author":"S. Kullback","year":"1968","unstructured":"Kullback S.: Information Theory and Statistics. Dover Publications, New York (1968)"},{"key":"263_CR35","doi-asserted-by":"crossref","unstructured":"Lee, M.L., Yang, L.H., Hsu, W., Yang, X.: XClust: clustering XML schemas for effective integration. In: 11th International Conference on Information and Knowledge Management (CIKM\u201902), McLean, Virginia (2002)","DOI":"10.1145\/584792.584841"},{"key":"263_CR36","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2606-0","volume-title":"An Introduction to Kolmogorov Complexity","author":"M. Li","year":"1997","unstructured":"Li M., Vit\u00e1nyi P.M.B.: An Introduction to Kolmogorov Complexity. Springer, (1997)"},{"issue":"1","key":"263_CR37","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/TKDE.2004.1264824","volume":"16","author":"W. Lian","year":"2004","unstructured":"Lian W., Cheung D.W.L., Mamoulis N., Yiu S.-M.: An efficient and scalable algorithm for clustering XML documents by structure. IEEE Trans. Knowl. Data Eng. (TKDE) 16(1), 82\u201396 (2004)","journal-title":"IEEE Trans. Knowl. Data Eng. (TKDE)"},{"key":"263_CR38","unstructured":"Martins, A.: String kernels and similarity measures for information retrieval. Technical report, Priberam, Lisbon, Portugal (2006)"},{"key":"263_CR39","unstructured":"Mesiti, M., Bertino, E., Guerrini, G.: An abstraction-based approach to measuring the structural similarity between two unordered XML documents. In: ISICT \u201903: Proceedings of the 1st International Symposium on Information and Communication Technologies, pp. 316\u2013321 (2003)"},{"key":"263_CR40","doi-asserted-by":"crossref","unstructured":"Nestorov, S., Abiteboul, S., Motwani, R.: Extracting schema from semistructured data. In: ACM SIGMOD International Conference on Management of Data, pp. 295\u2013306 (1998)","DOI":"10.1145\/276305.276331"},{"key":"263_CR41","unstructured":"Nierman, A., Jagadish, H.V.: Evaluating structural similarity in XML documents. In: Proceedings of the 5th International Workshop on the Web and Databases (WebDB), pp. 61\u201366, Madison, Wisconsin, (2002)"},{"key":"263_CR42","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/S0167-2789(03)00047-2","volume":"189","author":"A. Puglisi","year":"2003","unstructured":"Puglisi A., Benedetto D., Caglioti E., Loreto V., Vulpiani A.: Data compression and learning in time sequences analysis. Phys. D 189, 92\u2013107 (2003)","journal-title":"Phys. D"},{"key":"263_CR43","doi-asserted-by":"crossref","unstructured":"Santini, S., Jain, R.: Similarity measures. IEEE Trans. Pattern Anal. Mach. Intell. 21(9) (1999)","DOI":"10.1109\/34.790428"},{"issue":"6","key":"263_CR44","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/0020-0190(77)90064-3","volume":"6","author":"S. Selkow","year":"1977","unstructured":"Selkow S.: The tree-to-tree editing problem. Inf. Process. Lett. 6(6), 184\u2013186 (1977)","journal-title":"Inf. Process. Lett."},{"key":"263_CR45","doi-asserted-by":"crossref","unstructured":"Shannon, C.E.: The mathematical theory of communication. Bell Syst. Tech. J. 27, 379\u2013423, 623\u2013656 (1948)","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"263_CR46","volume-title":"Pattern Matching in Strings, Trees, and Arrays, chapter Approximate Tree Pattern Matching","author":"D. Shasha","year":"1995","unstructured":"Shasha D., Zhang K.: Pattern Matching in Strings, Trees, and Arrays, chapter Approximate Tree Pattern Matching. Oxford University Press, Oxford (1995)"},{"key":"263_CR47","volume-title":"Numerical Taxonomy","author":"P.H.A. Sneath","year":"1973","unstructured":"Sneath P.H.A., Sokal R.R.: Numerical Taxonomy. Freeman, San Francisco (1973)"},{"issue":"1","key":"263_CR48","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0019-9958(64)90223-2","volume":"7","author":"R. Solomonoff","year":"1964","unstructured":"Solomonoff R.: A formal theory of inductive inference, part I. Inf. Control 7(1), 1\u201322 (1964)","journal-title":"Inf. Control"},{"issue":"2","key":"263_CR49","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1016\/S0019-9958(64)90131-7","volume":"7","author":"R. Solomonoff","year":"1964","unstructured":"Solomonoff R.: A formal theory of inductive inference, part II. Inf. Control 7(2), 224\u2013254 (1964)","journal-title":"Inf. Control"},{"issue":"3","key":"263_CR50","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 26(3), 422\u2013433 (1979)","journal-title":"J. ACM"},{"key":"263_CR51","doi-asserted-by":"crossref","unstructured":"Theobald, A., Weikum, G.: The XXL search engine: ranked retrieval of XML data using indexes and ontologies. In: ACM SIGMOD International Conference on Management of Data, p. 615 (2002)","DOI":"10.1145\/564764.564768"},{"issue":"3","key":"263_CR52","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1007\/BF01206331","volume":"14","author":"E. Ukkonen","year":"1995","unstructured":"Ukkonen E.: On-line construction of suffix trees. Algorithmica 14(3), 249\u2013260 (1995)","journal-title":"Algorithmica"},{"issue":"4","key":"263_CR53","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1109\/69.298173","volume":"6","author":"J. Wang","year":"1994","unstructured":"Wang J., Zhang K., Jeong K., Shasha D.: A system for approximate tree matching. IEEE Trans. Knowl. Data Eng. 6(4), 559\u2013571 (1994)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"263_CR54","doi-asserted-by":"crossref","unstructured":"Weiner, P.: Linear pattern matching algorithms. In: 14th Annual Symposium on Found. of Computer Science (FOCS), pp. 1\u201311, Iowa City, Iowa (1973)","DOI":"10.1109\/SWAT.1973.13"},{"key":"263_CR55","volume-title":"Managing Gigabytes","author":"I.H. Witten","year":"1999","unstructured":"Witten I.H., Moffat A., Bell T.C.: Managing Gigabytes. Morgan Kaufmann, San Francisco (1999)"},{"issue":"6","key":"263_CR56","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":"3","key":"263_CR57","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1109\/TIT.1977.1055714","volume":"23","author":"J. Ziv","year":"1977","unstructured":"Ziv J., Lempel A.: A universal algorithm for sequential data compression. IEEE Trans. Inf. Theory 23(3), 337\u2013343 (1977)","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"4","key":"263_CR58","doi-asserted-by":"crossref","first-page":"1270","DOI":"10.1109\/18.243444","volume":"39","author":"J. Ziv","year":"1993","unstructured":"Ziv J., Merhav N.: A measure of relative entropy between individual sequences with application to universal classification. IEEE Trans. Inf. Theory 39(4), 1270\u20131279 (1993)","journal-title":"IEEE Trans. Inf. Theory"}],"container-title":["The VLDB Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-012-0263-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00778-012-0263-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00778-012-0263-0","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T10:27:26Z","timestamp":1686738446000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00778-012-0263-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,2,8]]},"references-count":58,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2012,10]]}},"alternative-id":["263"],"URL":"https:\/\/doi.org\/10.1007\/s00778-012-0263-0","relation":{},"ISSN":["1066-8888","0949-877X"],"issn-type":[{"value":"1066-8888","type":"print"},{"value":"0949-877X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012,2,8]]}}}