{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T13:58:56Z","timestamp":1753883936735,"version":"3.33.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2007,3,2]],"date-time":"2007-03-02T00:00:00Z","timestamp":1172793600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2007,3,2]],"date-time":"2007-03-02T00:00:00Z","timestamp":1172793600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["World Wide Web"],"published-print":{"date-parts":[[2007,6]]},"DOI":"10.1007\/s11280-007-0021-1","type":"journal-article","created":{"date-parts":[[2007,3,1]],"date-time":"2007-03-01T21:15:37Z","timestamp":1172783737000},"page":"157-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Information Extraction from Web Pages Using Presentation Regularities and Domain Knowledge"],"prefix":"10.1007","volume":"10","author":[{"given":"Srinivas","family":"Vadrevu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fatih","family":"Gelgi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hasan","family":"Davulcu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2007,3,2]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Agrawal, R., Imielinski, T., Swami, A.N.: Mining association rules between sets of items in large databases. In: ACM SIGMOD Conference on Management of Data, pp. 207\u2013216. Washington, D.C. (1993)","DOI":"10.1145\/170036.170072"},{"key":"21_CR2","first-page":"39","volume-title":"Introduction to Machine Learning, chapter 3","author":"E. Alpaydin","year":"2004","unstructured":"Alpaydin, E.: Introduction to Machine Learning, chapter 3, pp. 39\u201359. MIT Press, Cambridge, MA (2004)"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Arasu, A., Garcia-Molina, H.: Extracting structured data from web pages. In: ACM SIGMOD Conference on Management of Data, San Diego, USA (2003)","DOI":"10.1145\/872757.872799"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Ashish, N., Knoblock, C.A.: Semi-automatic wrapper generation for internet information sources. In: Conference on Cooperative Information Systems, pp. 160\u2013169 (1997)","DOI":"10.1109\/COOPIS.1997.613813"},{"key":"21_CR5","unstructured":"Cai, D., Yu, S., Wen, J.-R., Ma, W.-Y.: Vips: a vision-based page segmentation algorithm. Technical Report MSR-TR-2003-79, Microsoft Technical Report (2003)"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Chkrabarti, S.: Integrating the document object model with hyperlinks for enhanced topic distillation and information extraction. In: International World Wide Web (WWW) Conference (2001)","DOI":"10.1145\/371920.372054"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Cimiano, P., Ladwig, G., Staab, S.: Gimme\u2019 the context: context-driven automatic semantic annotation with c-pankow. In: The 14th International World Wide Web (WWW) Conference (2005)","DOI":"10.1145\/1060745.1060796"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Ciravegna, F., Chapman, S., Dingli, A., Wilks, Y.: Learning to harvest information for the semantic web. In: Proceedings of the 1st European Semantic Web Symposium, Heraklion, Greece (2004)","DOI":"10.1007\/978-3-540-25956-5_22"},{"issue":"5","key":"21_CR9","first-page":"731","volume":"51","author":"V. Crescenzi","year":"2004","unstructured":"Crescenzi, V., Mecca, G.: Automatic information extraction from large web sites. J. Artists\u2019 Choice Mus. 51(5), 731\u2013779 (2004)","journal-title":"J. Artists\u2019 Choice Mus."},{"issue":"1","key":"21_CR10","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.websem.2003.07.006","volume":"1","author":"S. Dill","year":"2003","unstructured":"Dill, S., Eiron, N., Gibson, D., Gruhl, D., Guha, R., Jhingran, A., Kanungo, T., McCurley, K.S., Rajagopalan, S., Tomkins, A., Tomlin, J.A., Zien, J.Y.: A case for automated large-scale semantic annotation. Journal of Web. Semantics 1(1), 115\u2013132 (2003)","journal-title":"Journal of Web Semantics"},{"key":"21_CR11","doi-asserted-by":"crossref","unstructured":"Etzioni, O., Cafarella, M., Downey, D., Kok, S., Popescu, A.-M., Shaked, T., Soderland, S., Weld, D.S., Yates, A.: Web-scale information extraction in knowitall. In: International World Wide Web (WWW) Conference (2004)","DOI":"10.1145\/988672.988687"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Garofalakis, M., Gionis, A., Rastogi, R., Seshadri, S., Shim, K.: XTRACT: a system for extracting document type descriptors from xml documents. In: ACM SIGMOD Conference on Management of Data (2000)","DOI":"10.1145\/342009.335409"},{"key":"21_CR13","unstructured":"Gelgi, F., Vadrevu, S., Davulcu, H.: Automatic extraction of relational models from the web data. Technical Report ASU-CSE-TR-06-009, Arizona State University, April (2006)"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Guha, R., McCool, R.: TAP: a semantic web toolkit. Semantic Web Journal (2003)","DOI":"10.2139\/ssrn.3199008"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Hearst, M.A.: Untangling text data mining. In: Association for Computational Linguistics (1999)","DOI":"10.3115\/1034678.1034679"},{"issue":"1\u20132","key":"21_CR16","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/S0004-3702(99)00100-9","volume":"118","author":"N. Kushmerick","year":"2000","unstructured":"Kushmerick, N.: Wrapper induction: efficiency and expressiveness. Artif. Intell. 118(1\u20132), 15\u201368 (2000)","journal-title":"Artif. Intell."},{"key":"21_CR17","unstructured":"Kushmerick, N., Weld, D.S., Doorenbos, R.B.: Wrapper induction for information extraction. In: Intl. Joint Conference on Artificial Intelligence (IJCAI), pp. 729\u2013737 (1997)"},{"key":"21_CR18","unstructured":"Liu, L., Pu, C., Han, W.: Xwrap: an xml-enabled wrapper construction system for web information sources. In: International Conference on Data Engineering (2000)"},{"key":"21_CR19","unstructured":"Muslea, I., Minton, S., Knoblock, C.: Stalker: learning extraction rules for semistructured. In: Workshop on AI and Information Integration (1998)"},{"key":"21_CR20","volume-title":"Proceedings of the 17th Conference of the American Association for Artificial Intelligence (AAAI)","author":"N. Noy","year":"2000","unstructured":"Noy, N., Musen, M.: Prompt: algorithm and tool for automated ontology merging and alignment. In: Proceedings of the 17th Conference of the American Association for Artificial Intelligence (AAAI). AAAI Press, Menlo Park, CA (2000)"},{"key":"21_CR21","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1093\/biomet\/18.1-2.105","volume":"18","author":"K. Pearson","year":"1926","unstructured":"Pearson, K.: On the coefficient of racial likeliness. Biometrica 18, 105\u2013117 (1926)","journal-title":"Biometrica"},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Vadrevu, S., Gelgi, F., Davulcu, H.: Semantic partitioning web pages. In: The 6th International Conference on Web Information Systems Engineering (WISE) (2005)","DOI":"10.1007\/11581062_9"},{"key":"21_CR23","unstructured":"Yang, G., Tan, W., Mukherjee, S., Ramakrishnan, I.V., Davulcu, H.: On the power of semantic partitioning of web documents. In: Workshop on Information Integration on the Web, Acapulco, Mexico (2003)"}],"container-title":["World Wide Web"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-007-0021-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11280-007-0021-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-007-0021-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11280-007-0021-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,14]],"date-time":"2025-01-14T12:28:20Z","timestamp":1736857700000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11280-007-0021-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,3,2]]},"references-count":23,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2007,6]]}},"alternative-id":["21"],"URL":"https:\/\/doi.org\/10.1007\/s11280-007-0021-1","relation":{},"ISSN":["1386-145X","1573-1413"],"issn-type":[{"type":"print","value":"1386-145X"},{"type":"electronic","value":"1573-1413"}],"subject":[],"published":{"date-parts":[[2007,3,2]]},"assertion":[{"value":"2 May 2006","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2006","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 January 2007","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2007","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}