{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T06:40:15Z","timestamp":1738910415953,"version":"3.37.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2009,1,27]],"date-time":"2009-01-27T00:00:00Z","timestamp":1233014400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2009,6]]},"DOI":"10.1007\/s11280-009-0059-3","type":"journal-article","created":{"date-parts":[[2009,1,26]],"date-time":"2009-01-26T10:42:46Z","timestamp":1232966566000},"page":"171-211","source":"Crossref","is-referenced-by-count":13,"title":["On Finding Templates on Web Collections"],"prefix":"10.1007","volume":"12","author":[{"given":"Karane","family":"Vieira","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andr\u00e9 Luiz","family":"da Costa Carvalho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Klessius","family":"Berlt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edleno S.","family":"de Moura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Altigran S.","family":"da Silva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juliana","family":"Freire","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2009,1,27]]},"reference":[{"key":"59_CR1","doi-asserted-by":"crossref","unstructured":"Bar-Yossef, Z., Rajagopalan, S.: Template detection via data mining and its applications. In: Proceedings of the International Conference on the World Wide Web, pp. 580\u2013591 (2002)","DOI":"10.1145\/511446.511522"},{"issue":"1","key":"59_CR2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11280-006-0008-3","volume":"10","author":"I. Beszteri","year":"2007","unstructured":"Beszteri, I., Vuorimaa, P.: Vertical navigation of layout adapted web documents. World Wide Web 10(1), 1\u201335 (2007)","journal-title":"World Wide Web"},{"key":"59_CR3","doi-asserted-by":"crossref","unstructured":"Chakrabarti, S., Joshi, M., Tawde, V.: Enhanced topic distillation using text, markup tags, and hyperlinks. In: Proceedings the of ACM Conference on Research and Development in Information Retrieval, pp. 208\u2013216 (2001)","DOI":"10.1145\/383952.383990"},{"key":"59_CR4","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1145\/1242572.1242582","volume-title":"WWW \u201907: Proceedings of the 16th International Conference on World Wide Web","author":"D. Chakrabarti","year":"2007","unstructured":"Chakrabarti, D., Kumar, R., Punera, K.: Page-level template detection via isotonic smoothing. In: WWW \u201907: Proceedings of the 16th International Conference on World Wide Web, pp. 61\u201370. ACM, New York, NY, USA (2007)"},{"key":"59_CR5","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 tree-to-tree correction problem. J. Algorithms 40, 135\u2013158 (2001)","journal-title":"J. Algorithms"},{"key":"59_CR6","doi-asserted-by":"crossref","first-page":"1094","DOI":"10.1145\/1141277.1141534","volume-title":"SAC \u201906: Proceedings of the 2006 ACM Symposium on Applied Computing","author":"L. Chen","year":"2006","unstructured":"Chen, L., Ye, S., Li, X.: Template detection for large scale search engines. In: SAC \u201906: Proceedings of the 2006 ACM Symposium on Applied Computing, pp. 1094\u20131098. ACM, New York, NY, USA (2006)"},{"issue":"3","key":"59_CR7","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.K.: A methodology for clustering xml documents by structure. Inf. Syst. 31(3), 187\u2013228 (2006)","journal-title":"Inf. Syst."},{"key":"59_CR8","doi-asserted-by":"crossref","unstructured":"de\u00a0Castro\u00a0Reis, D., Golgher, P.B., da\u00a0Silva, A.S., Laender, A.H.F.: Automatic web news extraction using tree edit distance. In: Proceedings of the International Conference on the World Wide Web, pp. 502\u2013511 (2004)","DOI":"10.1145\/988672.988740"},{"key":"59_CR9","doi-asserted-by":"crossref","unstructured":"Debnath, S., Mitra, P., Giles, C.L.: Automatic extraction of informative blocks from webpages. In: ACM Symposium on Applied Computing, pp. 1722\u20131726 (2005)","DOI":"10.1145\/1066677.1067065"},{"key":"59_CR10","doi-asserted-by":"crossref","unstructured":"Gibson, D., Punera, K., Tomkins, A.: The volume and evolution of web page templates. In: Proceedings of the International Conference on the World Wide Web\u2014Poster Session, pp. 830\u2013839. (2005)","DOI":"10.1145\/1062745.1062763"},{"key":"59_CR11","doi-asserted-by":"crossref","unstructured":"Joshi, S., Agrawal, N., Krishnapuram, R., Negi, S.: A bag of paths model for measuring structural similarity in web documents. In: Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, pp. 577\u2013582 (2003)","DOI":"10.1145\/956750.956822"},{"issue":"1","key":"59_CR12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11280-007-0018-9","volume":"11","author":"S. Khy","year":"2008","unstructured":"Khy, S., Ishikawa, Y., Kitagawa, H.: A novelty-based clustering method for on-line documents. World Wide Web 11(1), 1\u201337 (2008)","journal-title":"World Wide Web"},{"issue":"1","key":"59_CR13","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. 16(1), 82\u201396 (2004)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"2","key":"59_CR14","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1007\/s11280-008-0043-3","volume":"11","author":"J.A. Mac\u00edas","year":"2008","unstructured":"Mac\u00edas, J.A.: Intelligent assistance in authoring dynamically generated web interfaces. World Wide Web 11(2), 253\u2013286 (2008)","journal-title":"World Wide Web"},{"issue":"1","key":"59_CR15","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1145\/291469.291470","volume":"42","author":"J. Nielsen","year":"1999","unstructured":"Nielsen, J.: User interface directions for the web. Commun. ACM 42(1), 65\u201372 (1999)","journal-title":"Commun. ACM"},{"key":"59_CR16","unstructured":"Nierman, A., Jagadish, H.V.: Evaluating structural similarity in XML documents. In: Proceedings of the International Workshop on the Web and Databases (2002)"},{"key":"59_CR17","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1016\/0020-0190(77)90064-3","volume":"6","author":"S.M. Selkow","year":"1977","unstructured":"Selkow, S.M.: The tree-to-tree editing problem. Inf. Process. Lett. 6, 184\u2013186 (1977)","journal-title":"Inf. Process. Lett."},{"key":"59_CR18","doi-asserted-by":"crossref","unstructured":"Song, R., Liu, H., Wen, J.R., Ma, W.Y.: Learning block importance models for web pages. In: Proceedings of the International Conference on the World Wide Web, pp. 203\u2013211 (2004)","DOI":"10.1145\/988672.988700"},{"issue":"3","key":"59_CR19","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":"59_CR20","doi-asserted-by":"crossref","unstructured":"Valiente, G.: An efficient bottom-up distance between trees. In: Proceedings of the International Symposium on String Processing and Information Retrieval, pp. 212\u2013219. IEEE Computer Science Press (2001)","DOI":"10.1109\/SPIRE.2001.989761"},{"key":"59_CR21","doi-asserted-by":"crossref","unstructured":"Vieira, K., da\u00a0Silva, A.S., Pinto, N., de\u00a0Moura, E.S., Cavalcanti, J.M.B., Freire, J.: A fast and robust method for web page template detection and removal. In: Proceedings of the ACM International Conference on Information and Knowledge Management, Arlington, VA, USA, pp. 258\u2013267 (2006)","DOI":"10.1145\/1183614.1183654"},{"key":"59_CR22","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1016\/S0031-3203(99)00199-5","volume":"34","author":"J.T.L. Wang","year":"2001","unstructured":"Wang, J.T.L., Zhang, K.: Finding similar consensus between trees: an algorithm and a distance hierarchy. Pattern Recogn. 34, 127\u2013137 (2001)","journal-title":"Pattern Recogn."},{"issue":"7","key":"59_CR23","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1002\/spe.4380210706","volume":"21","author":"W. Yang","year":"1991","unstructured":"Yang, W.: Identifying syntactic differences between two programs. Softw. Pract. Exp. 21(7), 739\u2013755 (1991)","journal-title":"Softw. Pract. Exp."},{"key":"59_CR24","doi-asserted-by":"crossref","unstructured":"Yi, L., Liu, B., Li, X.: Eliminating noisy information in web pages for data mining. In: Proceedings of the International ACM Conference on Knowledge Discovery and Data Mining, pp. 296\u2013305 (2003)","DOI":"10.1145\/956755.956785"},{"issue":"2","key":"59_CR25","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1007\/s11280-007-0022-0","volume":"10","author":"Y. Zhai","year":"2007","unstructured":"Zhai, Y., Liu, B.: Extracting web data using instance-based learning. World Wide Web 10(2), 113\u2013132 (2007)","journal-title":"World Wide Web"},{"issue":"3","key":"59_CR26","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."}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-009-0059-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11280-009-0059-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-009-0059-3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T06:23:07Z","timestamp":1738909387000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11280-009-0059-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,1,27]]},"references-count":26,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2009,6]]}},"alternative-id":["59"],"URL":"https:\/\/doi.org\/10.1007\/s11280-009-0059-3","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"type":"print","value":"1386-145X"},{"type":"electronic","value":"1573-1413"}],"subject":[],"published":{"date-parts":[[2009,1,27]]}}}