{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T19:34:37Z","timestamp":1725564877084},"publisher-location":"Berlin, Heidelberg","reference-count":33,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540203629"},{"type":"electronic","value":"9783540397182"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2003]]},"DOI":"10.1007\/978-3-540-39718-2_34","type":"book-chapter","created":{"date-parts":[[2010,9,4]],"date-time":"2010-09-04T02:01:33Z","timestamp":1283565693000},"page":"533-549","source":"Crossref","is-referenced-by-count":29,"title":["Automatic Annotation of Content-Rich HTML Documents: Structural and Semantic Analysis"],"prefix":"10.1007","author":[{"given":"Saikat","family":"Mukherjee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guizhen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"I. V.","family":"Ramakrishnan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"unstructured":"WordNet, http:\/\/www.cogsci.princeton.edu\/~wn\/","key":"34_CR1"},{"doi-asserted-by":"crossref","unstructured":"Arasu, A., Garcia-Molina, H.: Extracting structured data from web pages. In: ACM SIGMOD (2003)","key":"34_CR2","DOI":"10.1145\/872757.872799"},{"key":"34_CR3","volume-title":"Weaving the Web","author":"T. Berners-Lee","year":"1999","unstructured":"Berners-Lee, T., Fischetti, M.: Weaving the Web. Harper, San Francisco (1999)"},{"doi-asserted-by":"crossref","unstructured":"Buttler, D., Liu, L., Pu, C.: A fully automated object extraction system for the world wide web. In: International Confernece on Distributed Computing Systems (ICDCS) (2001)","key":"34_CR4","DOI":"10.1109\/ICDSC.2001.918966"},{"doi-asserted-by":"crossref","unstructured":"Buyukkoten, O., Garcia-Molina, H., Paepcke, A.: Focussed web searching with PDAs. In: International World Wide Web Conference (2000)","key":"34_CR5","DOI":"10.1016\/S1389-1286(00)00060-8"},{"unstructured":"Chung, C.Y., Gertz, M., Sundaresan, N.: Reverse engineering for web data: From visual to semantic structures. In: ICDE (2002)","key":"34_CR6"},{"doi-asserted-by":"crossref","unstructured":"Cohen, W., Hurst, M., Jensen, L.: A flexible learning system for wrapping tables and lists in html documents. In: International World Wide Web Conference (2002)","key":"34_CR7","DOI":"10.1145\/511446.511477"},{"doi-asserted-by":"crossref","unstructured":"Crescenzi, V., Mecca, G., Merialdo, P.: Roadrunner: Towards automatic data extraction from large web sites. In: VLDB (2001)","key":"34_CR8","DOI":"10.1145\/564691.564778"},{"doi-asserted-by":"crossref","unstructured":"Dill, S., Eiron, N., Gibson, D., Gruhl, D., Guha, R., Jhingran, A., Kanungo, T., Rajagopalan, S., Tomkins, A., Tomlin, J., Yien, J.: SemTag and Seeker: Bootstrapping the semantic web via automated semantic annotation. In: International World Wide Web Conference (2003)","key":"34_CR9","DOI":"10.1145\/775152.775178"},{"doi-asserted-by":"crossref","unstructured":"Embley, D., Xu, L.: Record location and reconfiguration in unstructured multiple-record web documents. In: ACM International Workshop on the Web and Databases (WebDB) (2000)","key":"34_CR10","DOI":"10.1007\/3-540-45271-0_17"},{"doi-asserted-by":"crossref","unstructured":"Embley, D.W., Campbell, D.M., Smith, R.D., Liddle, S.W.: Ontology-based extraction and structuring of information from data-rich unstructured documents. In: International Conference on Information and Knowledge Management (CIKM) (1998)","key":"34_CR11","DOI":"10.1145\/288627.288641"},{"doi-asserted-by":"crossref","unstructured":"Embley, D.W., Jiang, Y., Ng, Y.-K.: Record-boundary discovery in web documents. In: ACM SIGMOD (1999)","key":"34_CR12","DOI":"10.1145\/304182.304223"},{"unstructured":"Fensel, D., Decker, S., Erdmann, M., Studer, R.: Ontobroker: Or how to enable intelligent access to the WWW. In: 11th Banff Knowledge Acquisition for Knowledge-Based Systems Workshop, Banff, Canada (1998)","key":"34_CR13"},{"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 (2000)","key":"34_CR14","DOI":"10.1145\/342009.335409"},{"unstructured":"Goldman, R., Widom, J.: DataGuides: Enabling query formulation and optimization in semistructured databases. In: VLDB (1997)","key":"34_CR15"},{"doi-asserted-by":"crossref","unstructured":"Grosof, B.N., Horrocks, I., Volz, R., Decker, S.: Description logic programms: Combining logic programs with description logic. In: International World Wide Web Conference (2003)","key":"34_CR16","DOI":"10.2139\/ssrn.460986"},{"doi-asserted-by":"crossref","unstructured":"Hammer, J., Garcia-Molina, H., Nestorov, S., Yerneni, R., Breunig, M.M., Vassalos, V.: Template-based wrappers in the TSIMMIS system. In: ACM SIGMOD (1997)","key":"34_CR17","DOI":"10.1145\/253260.253395"},{"doi-asserted-by":"crossref","unstructured":"Handschuh, S., Staab, S.: Authoring and annotation of web pages in CREAM. In: International World Wide Web Conference (2002)","key":"34_CR18","DOI":"10.1145\/511446.511506"},{"doi-asserted-by":"crossref","unstructured":"Handschuh, S., Staab, S., Volz, R.: On deep annotation. In: International World Wide Web Conference (2003)","key":"34_CR19","DOI":"10.1145\/775152.775214"},{"key":"34_CR20","doi-asserted-by":"crossref","first-page":"29","DOI":"10.7551\/mitpress\/6412.003.0004","volume-title":"Spinning the Semantic Web","author":"J. Heflin","year":"2003","unstructured":"Heflin, J., Hendler, J.A., Luke, S.: SHOE: A blueprint for the semantic web. In: Fensel, D., Hendler, J.A., Lieberman, H., Wahlster, W. (eds.) Spinning the Semantic Web, pp. 29\u201363. MIT Press, Cambridge (2003)"},{"doi-asserted-by":"crossref","unstructured":"Horrocks, I.: Benchmark analysis with FaCT. In: TABLEAUX (2000)","key":"34_CR21","DOI":"10.1007\/10722086_6"},{"unstructured":"Horrocks, I.: DAML+OIL: A description logic for the SemanticWeb. IEEE Bulletin of the Technical Committee on Data Engineering\u00a025(1) (March 2002)","key":"34_CR22"},{"key":"34_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/3-540-48005-6_15","volume-title":"The Semantic Web - ISWC 2002","author":"I. Horrocks","year":"2002","unstructured":"Horrocks, I., Tessaris, S.: Querying the semantic web: A formal approach. In: Horrocks, I., Hendler, J. (eds.) ISWC 2002. LNCS, vol.\u00a02342, p. 177. Springer, Heidelberg (2002)"},{"unstructured":"Lim, S.-J., Ng, Y.-K.: A automated change detection algorithm for HTML documents based on semantic hierarchies. In: ICDE (2001)","key":"34_CR24"},{"unstructured":"Liu, L., Pu, C., Han, W.: XWRAP: An XML-enabled wrapper construction system for web information sources. In: ICDE (2000)","key":"34_CR25"},{"doi-asserted-by":"crossref","unstructured":"Nestorov, S., Abiteboul, S., Motwani, R.: Extracting schema from semistructured data. In: ACM SIGMOD (1998)","key":"34_CR26","DOI":"10.1145\/276304.276331"},{"doi-asserted-by":"crossref","unstructured":"Papakonstantinou, Y., Vianu, V.: DTD inference for views of xml data. In: ACM PODS (2000)","key":"34_CR27","DOI":"10.1145\/335168.335173"},{"key":"34_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1007\/3-540-48005-6_28","volume-title":"The Semantic Web - ISWC 2002","author":"M. Sintek","year":"2002","unstructured":"Sintek, M., Decker, S.: TRIPLE \u2013 a query, inference, and transformation language for the semantic web. In: Horrocks, I., Hendler, J. (eds.) ISWC 2002. LNCS, vol.\u00a02342, p. 364. Springer, Heidelberg (2002)"},{"doi-asserted-by":"crossref","unstructured":"Staab, S., Angele, J., Decker, S., Erdmann, M., Hotho, A., Maedche, A., Schnurr, H.-P., Studerand, R., Sure, Y.: Semantic community web portals. In: International World Wide Web Conference (2000)","key":"34_CR29","DOI":"10.1016\/S1389-1286(00)00039-6"},{"unstructured":"Yang, G., Kifer, M.: $\\mathcal{F}$ lora-2: User\u2019s Manual (June 2002), http:\/\/flora.sourceforge.net\/","key":"34_CR30"},{"doi-asserted-by":"crossref","unstructured":"Yang, G., Kifer, M.: Well-founded optimism: Inheritance in frame-based knowledge bases. In: International Conference on Ontologies, Databases, and Applications of Semantics (ODBASE) (2002)","key":"34_CR31","DOI":"10.1007\/3-540-36124-3_65"},{"unstructured":"Yang, Y., Zhang, H.: HTML page analysis based on visual cues. In: International Conference on Document Analysis and Recognition (ICDAR) (2001)","key":"34_CR32"},{"doi-asserted-by":"crossref","unstructured":"Yu, S., Cai, D., Wen, J.-R., Ma, W.-Y.: Improving pseudo-relevance feedback in web information retrieval using web page segnmentation. In: International World Wide Web Conference (2003)","key":"34_CR33","DOI":"10.1145\/775152.775155"}],"container-title":["Lecture Notes in Computer Science","The Semantic Web - ISWC 2003"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-39718-2_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,30]],"date-time":"2024-03-30T03:43:08Z","timestamp":1711770188000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-39718-2_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003]]},"ISBN":["9783540203629","9783540397182"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-39718-2_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2003]]}}}