{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T02:43:45Z","timestamp":1783737825017,"version":"3.55.0"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2006,4,4]],"date-time":"2006-04-04T00:00:00Z","timestamp":1144108800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2006,7]]},"DOI":"10.1007\/s10115-006-0014-x","type":"journal-article","created":{"date-parts":[[2006,4,3]],"date-time":"2006-04-03T12:08:23Z","timestamp":1144066103000},"page":"1-15","source":"Crossref","is-referenced-by-count":20,"title":["Visual information extraction"],"prefix":"10.1007","volume":"10","author":[{"given":"Yonatan","family":"Aumann","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronen","family":"Feldman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yair","family":"Liberzon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Rosenfeld","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Schler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2006,4,4]]},"reference":[{"key":"14_CR1","unstructured":"Proceedings of the seventh message understanding conference (MUC-7) Available at: http:\/\/www.itl.nist.gov\/iaui\/894.02\/related_projects\/muc\/proceedings\/muc_7_toc.html"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Proceedings of the third message understanding conference (MUC-3) (1991) Morgan Kaufmann","DOI":"10.3115\/1071958.1071960"},{"key":"14_CR3","unstructured":"Proceedings of the forth message understanding conference (MUC-4) (1992) Morgan Kaufmann"},{"key":"14_CR4","unstructured":"Proceedings of the fifth message understanding conference (MUC-5) (1993) Morgan Kaufmann"},{"key":"14_CR5","unstructured":"Proceedings of the sixth message understanding conference (MUC-6) (1995) Morgan Kaufmann"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Altamura O, Esposito F, Malerba D (2001) Transforming paper documents into XML format with WISDOM ++ . Int J Document Anal Recog 4(1):2\u201317","DOI":"10.1007\/PL00013569"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Anjewierden A. AIDAS: incremental logical structure discovery in pdf documents. In: Proceedings of the sixth international conference on document analysis and recognition (ICDAR), pp 374\u2013378","DOI":"10.1109\/ICDAR.2001.953816"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Ashish N, Knoblock C (1997) Wrapper generation for semi-structured internet sources. In: Proceedings of the workshop on management of semistructured data, Tucson","DOI":"10.1145\/271074.271078"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Berardi M, Lapi M, Malerba D (2004) An integrated approach for automatic semantic structure extraction in document images. In: Marinai S, Dengel A (eds) Document analysis systems. Lecture Notes in Computer Science, vol 3163. Springer-Verlag, Berlin Heidelberg New York, pp 179\u2013190","DOI":"10.1007\/978-3-540-28640-0_17"},{"issue":"2","key":"14_CR10","first-page":"83","volume":"14","author":"L Bright","year":"1999","unstructured":"Bright L, Gruser JR, Raschid L, Vidal ME (1999) A wrapper generation toolkit to specify and construct wrappers for Web accessible data sources (WebSources). Int J Comput Syst Sci Eng 14(2):83\u201397","journal-title":"Int J Comput Syst Sci Eng"},{"key":"14_CR11","unstructured":"Califf ME, Mooney RJ (1999) Relational learning of pattern-match rules for information extraction. In: AAAI99\/IAAI99: Proceedings of the sixteenth national conference on artificial intelligence and the eleventh innovative applications of artificial intelligence conference innovative applications of artificial intelligence, pp 328\u2013334"},{"key":"14_CR12","unstructured":"Chao H, Beretta G, Sang H (2001) PDF document layout study with page elements and bounding boxes. In: Workshop on document layout interpretation and its applications (DLIA2001)"},{"key":"14_CR13","unstructured":"Eikvil L (1999) Information extraction from world wide web \u2013 a survey. Technical Report 945, Norweigan Computing Center"},{"issue":"2\/3","key":"14_CR14","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1023\/A:1008735902918","volume":"14","author":"F Esposito","year":"2000","unstructured":"Esposito F, Malerba D, Lisi FA (2000) Machine learning for intelligent processing of printed documents. J Intell Inform Syst 14(2\/3):178\u2013198","journal-title":"J Intell Inform Syst"},{"issue":"7","key":"14_CR15","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1145\/176789.176797","volume":"37","author":"O Etzioni","year":"1994","unstructured":"Etzioni O, Weld D (1994) A softbot-based interface to the internet. Commun ACM 37(7):72\u201376","journal-title":"Commun ACM"},{"key":"14_CR16","unstructured":"Freitag D (1998) Toward general-purpose learning for information extraction. In: Proceedings of the thirty-sixth annual meeting of the association for computational linguistics and seventeenth international conference on computational linguistics, pp 404\u2013408"},{"key":"14_CR17","unstructured":"Friedman M, Weld DS (1997) Efficiently executing information-gathering plans. In: 15th international joint conference on artificial intelligence, Nagoya, Japan, pp 785\u2013791"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Futrelle RP, Shao M, Cieslik C, Grimes AE (2003) Extraction, layout analysis and classification of diagrams in PDF documents. In: Proceedings of the seventh international conference on document analysis and recognition, IEEE, pp 1007\u20131015","DOI":"10.1109\/ICDAR.2003.1227811"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Hammer J, Garc\u0131a-Molina H, Nestorov S, Yerneni R, Breunig M, Vassalos V (1997) Template-based wrappers in the TSIMMIS system. In: Proceedings of the twenty-third ACM SIGMOD international conference on management of data, pp 532\u2013535","DOI":"10.1145\/253260.253395"},{"issue":"8","key":"14_CR20","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1016\/S0306-4379(98)00027-1","volume":"23","author":"CN Hsu","year":"1998","unstructured":"Hsu CN, Dung MT (1998) Generating finite-state transducers for semi-structured data extraction from the web. Inform Syst 23(8):521\u2013538","journal-title":"Inform Syst"},{"issue":"1\u20132","key":"14_CR21","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/S0004-3702(99)00100-9","volume":"118","author":"N Kushmerick","year":"2000","unstructured":"Kushmerick N (2000) Wrapper induction: Efficiency and expressiveness. Artif Intell 118(1\u20132):15\u201368","journal-title":"Artif Intell"},{"key":"14_CR22","unstructured":"Lewis JW (1991) Wrappers: integration utilities and services for the DICE architecture. In: Proceedings of the second national symposium on concurrent engineering, pp 445\u2013457"},{"issue":"2\/3","key":"14_CR23","first-page":"207","volume":"8","author":"WS Lovegrove","year":"1995","unstructured":"Lovegrove WS, Brailsford DF (1995) Document analysis of PDF files: methods, results and implications. Electron Publish 8(2\/3):207\u2013220","journal-title":"Electron Publish"},{"issue":"1\/2","key":"14_CR24","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1023\/A:1010022931168","volume":"4","author":"I Muslea","year":"2001","unstructured":"Muslea I, Minton S, Knoblock CA (2001) Hierarchical wrapper induction for semistructured information sources. Autonom Agents Multi-Agent Syst 4(1\/2):93\u2013114","journal-title":"Autonom Agents Multi-Agent Syst"},{"issue":"1","key":"14_CR25","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1023\/A:1008162616689","volume":"38","author":"C Papageorgiou","year":"2000","unstructured":"Papageorgiou C, Poggio T (2000) A trainable system for object detection. Int J Comput Vis 38(1):15\u201333","journal-title":"Int J Comput Vis"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Papakonstantinou Y, Gupta A, Garcia-Molina H, Ullman JD (1995) A query translation scheme for rapid implementation of wrappers. In: 4th intenational conference on deductive and object-oriented databases, LNCS, vol E1013. Springer, Berlin Heidelberg New York, pp 319\u2013344","DOI":"10.1007\/3-540-60608-4_40"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Poggio T, Edelman S (1990) Network that learns to recognize 3D objects. Nature 343:263\u2013266","DOI":"10.1038\/343263a0"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Rosenfeld B, Feldman R, Aumann Y (2002) Structural extraction from visual layout of documents. In: Proceedings of the eleventh international conference on information and knowledge management, pp 203\u2013210","DOI":"10.1145\/584792.584828"},{"issue":"1","key":"14_CR29","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/64.577468","volume":"12","author":"E Selberg","year":"1997","unstructured":"Selberg E, Etzioni O (1997) The MetaCrawler architecture for resource aggregation on the Web. IEEE Expert 12(1):8\u201314","journal-title":"IEEE Expert"},{"issue":"1\u20133","key":"14_CR30","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1023\/A:1007562322031","volume":"34","author":"S Soderland","year":"1999","unstructured":"Soderland S (1999) Learning information extraction rules for semi-structured and free text. Mach Learn 34(1\u20133):233\u2013272","journal-title":"Mach Learn"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-006-0014-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-006-0014-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-006-0014-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T06:22:58Z","timestamp":1736317378000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-006-0014-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,4,4]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2006,7]]}},"alternative-id":["14"],"URL":"https:\/\/doi.org\/10.1007\/s10115-006-0014-x","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,4,4]]}}}