{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T13:37:15Z","timestamp":1773409035872,"version":"3.50.1"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2011,4,9]],"date-time":"2011-04-09T00:00:00Z","timestamp":1302307200000},"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":[[2012,3]]},"DOI":"10.1007\/s10115-011-0394-4","type":"journal-article","created":{"date-parts":[[2011,4,8]],"date-time":"2011-04-08T11:40:02Z","timestamp":1302262802000},"page":"667-692","source":"Crossref","is-referenced-by-count":8,"title":["A spatial relation-based framework to perform visual information extraction"],"prefix":"10.1007","volume":"30","author":[{"given":"Giuseppe","family":"Della Penna","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Magazzeni","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergio","family":"Orefice","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2011,4,9]]},"reference":[{"key":"394_CR1","doi-asserted-by":"crossref","unstructured":"Anjewierden A (2001) 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"},{"issue":"1","key":"394_CR2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10115-006-0014-x","volume":"10","author":"Y Aumann","year":"2006","unstructured":"Aumann Y, Feldman R, Liberzon Y, Rosenfeld B, Schler J (2006) Visual information extraction. Knowl Inf Syst 10(1): 1\u201315","journal-title":"Knowl Inf Syst"},{"key":"394_CR3","unstructured":"Chao H, Beretta G and Sang H (2001) Pdf document layout study with page elements and bounding boxes. In: Workshop on document layout interpretation and its applications (DLIA2001)"},{"issue":"6","key":"394_CR4","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1006\/jvlc.2002.0234","volume":"13","author":"G Costagliola","year":"2002","unstructured":"Costagliola G, De Lucia A, Orefice S, Polese G (2002) A classification framework to support the design of visual languages. J Vis Lang Comput 13(6): 573\u2013600","journal-title":"J Vis Lang Comput"},{"issue":"8","key":"394_CR5","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1016\/S0306-4379(98)00028-3","volume":"23","author":"V Crescenzi","year":"1998","unstructured":"Crescenzi V, Mecca G (1998) Grammars have exceptions. Inf Syst 23(8): 539\u2013565","journal-title":"Inf Syst"},{"key":"394_CR6","unstructured":"Della Penna G, Magazzeni D, Orefice S (2009) A graphical tool to support visual information extraction. In: Proceedings of DMS 2009 (VLC workshop). Knowledge Systems Institute, pp 329\u2013334"},{"issue":"1","key":"394_CR7","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.jvlc.2009.06.001","volume":"21","author":"G Della Penna","year":"2010","unstructured":"Della Penna G, Magazzeni D, Orefice S (2010) Visual extraction of information from web pages. J Vis Lang Comput 21(1): 23\u201332","journal-title":"J Vis Lang Comput"},{"key":"394_CR8","unstructured":"Environmental Systems Research Institute, Inc. (1998) Esri shapefile technical description. http:\/\/www.esri.com\/library\/whitepapers\/pdfs\/shapefile.pdf"},{"key":"394_CR9","doi-asserted-by":"crossref","unstructured":"Fazzinga B, Flesca S, Tagarelli A (2009) Schema-based web wrapping. Knowl Inf Syst, pp 1\u201347. doi: 10.1007\/s10115-009-0275-2","DOI":"10.1007\/s10115-009-0275-2"},{"key":"394_CR10","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, pp 1007\u20131015","DOI":"10.1109\/ICDAR.2003.1227811"},{"key":"394_CR11","unstructured":"Gatterbauer W, Bohunsky P (2006) Table extraction using spatial reasoning on the CSS2 visual box model. In: Proceedings of the 21st national conference on artificial intelligence (AAAI 2006). AAAI, MIT Press"},{"key":"394_CR12","doi-asserted-by":"crossref","unstructured":"Gatterbauer W, Bohunsky P, Herzog M, Kr\u00fcpl B, Pollak B (2007) Towards domain-independent information extraction from web tables. In: WWW \u201907: proceedings of the 16th international conference on world wide web. ACM, New York, USA, pp 71\u201380","DOI":"10.1145\/1242572.1242583"},{"key":"394_CR13","doi-asserted-by":"crossref","unstructured":"Gottlob G, Koch C, Baumgartner R, Herzog M, Flesca S (2004) The LIXTO data extraction project\u2014back and forth between theory and practice. In: Proceedings of the symposium on principles of database systems (PODS-04)","DOI":"10.1145\/1055558.1055560"},{"key":"394_CR14","doi-asserted-by":"crossref","unstructured":"Gu X, Chen J, Ma W, Chen G (2002) Visual based content understanding towards web adaptation. In: Proceedings of the second international conference on adaptive hypermedia and adaptive web-based systems AH\u201902. LNCS, vol 2347. Springer, pp 164\u2013173","DOI":"10.1007\/3-540-47952-X_18"},{"key":"394_CR15","doi-asserted-by":"crossref","unstructured":"Hammer J, McHugh J, Garcia-Molina H (1997) Semistructured data: The TSIMMIS experience. In: Advances in databases and information systems, pp 1\u20138","DOI":"10.14236\/ewic\/ADBIS1997.22"},{"key":"394_CR16","doi-asserted-by":"crossref","unstructured":"Jiang L, Wang J, An N, Wang S, Zhan J, Li L (2009) GRAPE: a graph-based framework for disambiguating people appearances in web search. In: Proceedings of IEEE international conference on data mining. IEEE Computer Society, pp 199\u2013208","DOI":"10.1109\/ICDM.2009.25"},{"issue":"2","key":"394_CR17","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/565117.565137","volume":"31","author":"AHF Laender","year":"2002","unstructured":"Laender AHF, Ribeiro-Neto BA, da Silva AS, Teixeira JS (2002) A brief survey of web data extraction tools. SIGMOD Rec 31(2): 84\u201393","journal-title":"SIGMOD Rec"},{"issue":"2","key":"394_CR18","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/S0169-023X(01)00047-7","volume":"40","author":"AHF Laender","year":"2002","unstructured":"Laender AHF, Ribeiro-Neto B, da Silva AS (2002) DEByE\u2014data extraction by example. Data Knowl Eng 40(2): 121\u2013154","journal-title":"Data Knowl Eng"},{"key":"394_CR19","unstructured":"Lam M, Gong Z (2005) Web information extraction. In: Proceedings of the IEEE international conference on information acquisition"},{"issue":"2","key":"394_CR20","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 Publ 8(2): 207\u2013220","journal-title":"Electron Publ"},{"key":"394_CR21","doi-asserted-by":"crossref","unstructured":"Menard P, Ratte S (2010) Classifier-based acronym extraction for business documents. Knowl Inf Syst pp 1\u201330. doi: 10.1007\/s10115-010-0341-9","DOI":"10.1007\/s10115-010-0341-9"},{"issue":"1","key":"394_CR22","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1007\/s10115-007-0110-6","volume":"17","author":"B Rosenfeld","year":"2008","unstructured":"Rosenfeld B, Feldman R (2008) Self-supervised relation extraction from the web. Knowl Inf Syst 17(1): 17\u201333","journal-title":"Knowl Inf Syst"},{"key":"394_CR23","unstructured":"Sandvik B (2009) World borders dataset. http:\/\/thematicmapping.org\/downloads\/world_borders.php"},{"key":"394_CR24","unstructured":"Snoussi H, Magnin L, Nie J (2002) Towards an ontology-based web data extraction. In: BASeWEB proceedings of the fifteenth Canadian conference on artificial intelligence AI 2002"},{"issue":"1\u20133","key":"394_CR25","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"},{"key":"394_CR26","unstructured":"Steward S (2006) pdftk: The pdf toolkit. http:\/\/www.accesspdf.com\/pdftk\/"},{"key":"394_CR27","unstructured":"Wimalasuriya DC, Dou D (2009) Using multiple ontologies in information extraction. In: Proceedings of CIKM, pp 235\u2013244"},{"issue":"4","key":"394_CR28","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1109\/TKDE.2009.111","volume":"22","author":"T-L Wong","year":"2010","unstructured":"Wong T-L, Lam W (2010) Learning to adapt web information extraction knowledge and discovering new attributes via a bayesian approach. IEEE Trans Knowl Data Eng 22(4): 523\u2013536","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"394_CR29","unstructured":"Yang Y, Zhang H (2001) HTML page analysis based on visual cues. In: ICDAR \u201901: proceedings of the sixth international conference on document analysis and recognition. IEEE Computer Society, Washington, DC, USA, pp 859\u2013864"},{"key":"394_CR30","doi-asserted-by":"crossref","unstructured":"Zhai Y, Liu B (2005) Web data extraction based on partial tree alignment. In: WWW \u201905: proceedings of the 14th international conference on world wide web. ACM, New York, USA, pp 76\u201385","DOI":"10.1145\/1060745.1060761"},{"key":"394_CR31","doi-asserted-by":"crossref","unstructured":"Zhao H, Meng W, Wu Z, Raghavan V, Yu C (2005) Fully automatic wrapper generation for search engines. In: WWW \u201905: proceedings of the 14th international conference on World Wide Web. ACM, New York, USA, pp 66\u201375","DOI":"10.1145\/1060745.1060760"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-011-0394-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-011-0394-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-011-0394-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,18]],"date-time":"2020-06-18T02:21:21Z","timestamp":1592446881000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-011-0394-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4,9]]},"references-count":31,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2012,3]]}},"alternative-id":["394"],"URL":"https:\/\/doi.org\/10.1007\/s10115-011-0394-4","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011,4,9]]}}}