{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T08:03:40Z","timestamp":1783065820349,"version":"3.54.6"},"publisher-location":"Berlin, Heidelberg","reference-count":35,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540762799","type":"print"},{"value":"9783540762805","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008]]},"DOI":"10.1007\/978-3-540-76280-5_5","type":"book-chapter","created":{"date-parts":[[2007,12,26]],"date-time":"2007-12-26T21:08:14Z","timestamp":1198703294000},"page":"105-138","source":"Crossref","is-referenced-by-count":24,"title":["Machine Learning for Digital Document Processing: from Layout Analysis to Metadata Extraction"],"prefix":"10.1007","author":[{"given":"Floriana","family":"Esposito","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Ferilli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teresa M. A.","family":"Basile","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicola","family":"Di Mauro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"5_CR1_Ref","unstructured":"Esposito, F., Malerba, D., Semeraro, G., Ferilli, S., Altamura, O., Basile, T.M.A., Berardi, M., Ceci, M., Mauro, N.D.: Machine learning methods for automatically processing historical documents: From paper acquisition to XML transformation. In: Proceedings of the First International Workshop on Docu- ment Image Analysis for Libraries (DIAL 2004). (2004) 328-335"},{"issue":"(5)","key":"5_CR2_Ref","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1038\/scientificamerican0501-34","volume":"284","author":"T Berners Lee","year":"2001","unstructured":"Berners Lee, T., Hendler, J., Lassila, O.: The semantic web. Scientific American 284 (5) (2001) 34-43","journal-title":"Scientific American"},{"issue":"(2)","key":"5_CR3_Ref","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1023\/A:1022699900025","volume":"4","author":"PE Utgoff","year":"1989","unstructured":"Utgoff, P.E.: Incremental induction of decision trees. Machine Learning 4(2) (1989) 161-186","journal-title":"Machine Learning"},{"key":"5_CR4_Ref","first-page":"409","volume-title":"Advances in Neural Information Processing Systems (NIPS 2000)","author":"G Cauwenberghs","year":"2000","unstructured":"Cauwenberghs, G., Poggio, T.: Incremental and decremental support vector ma-chine learning. In: Advances in Neural Information Processing Systems (NIPS 2000). Volume 13., Cambridge, MA, USA, MIT Press (2000) 409-415"},{"key":"5_CR5_Ref","unstructured":"Solomonoff, R.: Progress in incremental machine learning. In: NIPS Workshop on Universal Learning Algorithms and Optimal Search, Dec. 14, 2002, Whistler, B.C., Canada, 27 pp. (2003)"},{"key":"5_CR6_Ref","unstructured":"Wong, W., Fu, A.: Incremental document clustering for web page classifica-tion. In: IEEE 2000 Int. Conf. on Info. Society in the 21st century: emerging technologies and new challenges (IS2000), Nov 5-8, 2000, Japan. (2000)"},{"issue":"(1-2)","key":"5_CR7_Ref","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/S0004-3702(96)00034-3","volume":"89","author":"TG Dietterich","year":"1997","unstructured":"Dietterich, T.G., Lathrop, R.H., Lozano-Perez, T.: Solving the multiple instance problem with axis-parallel rectangles. Artificial Intelligence 89(1-2) (1997) 31-71","journal-title":"Artificial Intelligence"},{"key":"5_CR8_Ref","doi-asserted-by":"crossref","unstructured":"Breuel, T.M.: Two geometric algorithms for layout analysis. In: Workshop on Document Analysis Systems. (2002)","DOI":"10.1007\/3-540-45869-7_23"},{"key":"5_CR9_Ref","unstructured":"Glunz, W.: pstoedit - a tool converting postscript and PDF files into various vector graphic formats (2007) (\n                  http:\/\/www.pstoedit.net\n                  \n                )."},{"key":"5_CR10_Ref","unstructured":"Adobe Systems Inc.: PostScript language reference manual - 2nd ed. Addison Wesley (1990)"},{"key":"5_CR11_Ref","unstructured":"Adobe Systems Inc.: PDF Reference version 1.3 - 2nd ed. Addison Wesley (2000)"},{"issue":"(8\/9)","key":"5_CR12_Ref","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1080\/713827255","volume":"17","author":"F Esposito","year":"2003","unstructured":"Esposito, F., Ferilli, S., Fanizzi, N., Basile, T.M., Di Mauro, N.: Incremental multistrategy learning for document processing. Applied Artificial Intelligence: An Internationa Journal 17(8\/9) (2003) 859-883","journal-title":"Applied Artificial Intelligence: An Internationa Journal"},{"issue":"\/20","key":"5_CR13_Ref","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1016\/0743-1066(94)90035-3","volume":"19","author":"S Muggleton","year":"1994","unstructured":"Muggleton, S., Raedt, L.D.: Inductive logic programming: Theory and methods. Journal of Logic Programming 19\/20 (1994) 629-679","journal-title":"Journal of Logic Programming"},{"key":"5_CR14_Ref","doi-asserted-by":"crossref","unstructured":"Semeraro, G., Esposito, F., Malerba, D., Fanizzi, N., Ferilli, S.: A logic frame- work for the incremental inductive synthesis of datalog theories. In Fuchs, N., ed.: Proceedings of the 7th International Workshop on Logic Program Synthesis and Transformation. Volume 1463 of LNCS., Springer (1998) 300-321","DOI":"10.1007\/3-540-49674-2_16"},{"key":"5_CR15_Ref","unstructured":"Becker, J.: Inductive learning of decision rules with exceptions: Methodology and experimentation. Master\u2019s thesis, Dept. of Computer Science, University of Illinois at Urbana-Champaign, Urbana, Illinois (1985) B.S. diss., UIUCDCS-F-85-945"},{"key":"5_CR16_Ref","unstructured":"Michalski, R.: Inferential theory of learning. developing foundations for mul-tistrategy learning. In Michalski, R., Tecuci, G., eds.: Machine Learning. A Multistrategy Approach. Volume IV. Morgan Kaufmann (1994) 3-61"},{"key":"5_CR17_Ref","volume-title":"Proceedings of the 1st Pacific Rim International Conference on Artificial Intelligence","author":"A Kakas","year":"1990","unstructured":"Kakas, A., Mancarella, P.: On the relation of truth maintenance and abduction. In: Proceedings of the 1st Pacific Rim International Conference on Artificial Intelligence, Nagoya, Japan (1990)"},{"key":"5_CR18_Ref","unstructured":"Zucker, J.D.: Semantic abstraction for concept representation and learning. In Michalski, R.S., Saitta, L., eds.: Proceedings of the 4th International Workshop on Multistrategy Learning. (1998) 157-164"},{"issue":"(2)","key":"5_CR19_Ref","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1080\/136588197242428","volume":"11","author":"D Papadias","year":"1997","unstructured":"Papadias, D., Theodoridis, Y.: Spatial relations, minimum bounding rectangles, and spatial data structures. International Journal of Geographical Information Science 11(2) (1997) 111-138","journal-title":"International Journal of Geographical Information Science"},{"key":"5_CR20_Ref","doi-asserted-by":"crossref","unstructured":"Egenhofer, M.: Reasoning about binary topological relations. In Gunther, O., Schek, H.J., eds.: Second Symposium on Large Spatial Databases. Volume 525 of Lecture Notes in Computer Science., Springer (1991) 143-160","DOI":"10.1007\/3-540-54414-3_36"},{"issue":"(6)","key":"5_CR21_Ref","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","volume":"41","author":"SC Deerwester","year":"1990","unstructured":"Deerwester, S.C., Dumais, S.T., Landauer, T.K., Furnas, G.W., Harshman, R.A.: Indexing by Latent Semantic Analysis. Journal of the American Society of Information Science 41(6) (1990) 391-407","journal-title":"Journal of the American Society of Information Science"},{"key":"5_CR22_Ref","unstructured":".Baeza-Yates, R.A., Ribeiro-Neto, B.A.: Modern Information Retrieval. ACM Press \/ Addison-Wesley (1999)"},{"issue":"(4)","key":"5_CR23_Ref","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1137\/1037127","volume":"37","author":"MW Berry","year":"1995","unstructured":"Berry, M.W., Dumais, S.T., O\u2019Brien, G.W.: Using linear algebra for intelligent information retrieval. SIAM Rev. 37(4) (1995) 573-595","journal-title":"SIAM Rev."},{"key":"5_CR24_Ref","unstructured":"O\u2019Brien, G.W.: Information management tools for updating an SVD-encoded in-dexing scheme. Technical Report UT-CS-94-258, University of Tennessee (1994)"},{"key":"5_CR25_Ref","first-page":"313","volume-title":"Readings in information retrieval","author":"MF Porter","year":"1997","unstructured":"Porter, M.F.: An algorithm for suffix stripping. In Karen, J.S., Willet, P., eds.: Readings in information retrieval. Morgan Kaufmann Publishers Inc., San Fran-cisco, CA, USA (1997) 313-316"},{"key":"5_CR26_Ref","unstructured":"Di Mauro, N., Basile, T.M.A., Ferilli, S.: GRAPE: An expert review assignment component for scientific conference management systems. In: Innovations in Ap-plied Artificial Intelligence: 18th International Conference on Industrial and En-gineering Applications of Artificial Intelligence and Expert Systems (IEA\/AIE 2005). Volume 3533 of Lecture Notes in Computer Science., Springer Verlag (2005) 789-798"},{"issue":"(1)","key":"5_CR27_Ref","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/34.824820","volume":"22","author":"G Nagy","year":"2000","unstructured":"Nagy, G.: Twenty years of document image analysis in PAMI. IEEE Transac-tions on Pattern Analysis and Machine Intelligence 22(1) (2000) 38-62","journal-title":"IEEE Transac-tions on Pattern Analysis and Machine Intelligence"},{"key":"5_CR28_Ref","doi-asserted-by":"crossref","unstructured":"Futrelle, R.P., Shao, M., Cieslik, C., Grimes, A.E.: Extraction, layout analysis and classification of diagrams in PDF documents. In: Proceedings of Seventh In-ternational Conference on Document Analysis and Recognition (ICDAR 2003). (2003) 1007-1014","DOI":"10.1109\/ICDAR.2003.1227811"},{"key":"5_CR29_Ref","unstructured":"Chao, H.: Graphics extraction in PDF document. In Kanungo, T., Smith, E.H.B., Hu, J., Kantor, P.B., eds.: Proceedings of SPIE - The International Society for Optical Engineering. Volume 5010. (2003) 317-325"},{"key":"5_CR30_Ref","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1109\/ICDAR.2003.1227692","volume-title":"Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003)","author":"JY Ramel","year":"2003","unstructured":"Ramel, J.Y., Crucianu, M., Vincent, N., Faure, C.: Detection, extraction and representation of tables. In: Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR 2003), Washington, DC, USA, IEEE Computer Society (2003) 374-378"},{"key":"5_CR31_Ref","doi-asserted-by":"crossref","unstructured":"Chao, H., Fan, J.: Layout and content extraction for pdf documents. In: Doc-ument Analysis Systems VI, Proceeding of the Sixth International Workshop (DAS 2004). Volume 3163 of Lecture Notes in Computer Science., Springer Ver-lag (2004) 213-224","DOI":"10.1007\/978-3-540-28640-0_20"},{"issue":"(2-3)","key":"5_CR32_Ref","first-page":"207","volume":"8","author":"WS Lovegrove","year":"1995","unstructured":"Lovegrove, W.S., Brailsford, D.F.: Document analysis of PDF files: methods, results and implications. Electronic Publishing - Origination, Dissemination and Design 8(2-3) (1995) 207-220","journal-title":"Electronic Publishing - Origination, Dissemination and Design"},{"key":"5_CR33_Ref","first-page":"212","volume-title":"Xed: A new tool for extract-ing hidden structures from electronic documents. In: DIAL \u201904: Proceedings of the First International Workshop on Document Image Analysis for Libraries (DIAL\u201904)","author":"K Hadjar","year":"2004","unstructured":"Hadjar, K., Rigamonti, M., Lalanne, D., Ingold, R.: Xed: A new tool for extract-ing hidden structures from electronic documents. In: DIAL \u201904: Proceedings of the First International Workshop on Document Image Analysis for Libraries (DIAL\u201904), Washington, DC, USA, IEEE Computer Society (2004) 212"},{"key":"5_CR34_Ref","doi-asserted-by":"publisher","first-page":"1050","DOI":"10.1109\/ICDAR.2005.242","volume-title":"ICDAR \u201905: Proceedings of the Eighth International Conference on Document Analysis and Recognition","author":"M Rigamonti","year":"2005","unstructured":"Rigamonti, M., Bloechle, J.L., Hadjar, K., Lalanne, D., Ingold, R.: Towards a canonical and structured representation of PDF documents through reverse en-gineering. In: ICDAR \u201905: Proceedings of the Eighth International Conference on Document Analysis and Recognition, Washington, DC, USA, IEEE Computer Society (2005) 1050-1055"},{"key":"5_CR35_Ref","doi-asserted-by":"crossref","unstructured":"Anjewierden, A.: AIDAS: Incremental logical structure discovery in pdf docu-ments. In: Proceedings of Sixth International Conference on Document Analysis and Recognition (ICDAR 2001). (2001) 374-378","DOI":"10.1109\/ICDAR.2001.953816"}],"container-title":["Studies in Computational Intelligence","Machine Learning in Document Analysis and Recognition"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-76280-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,10]],"date-time":"2019-03-10T14:44:55Z","timestamp":1552229095000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-76280-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008]]},"ISBN":["9783540762799","9783540762805"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-76280-5_5","relation":{},"ISSN":["1860-949X"],"issn-type":[{"value":"1860-949X","type":"print"}],"subject":[],"published":{"date-parts":[[2008]]}}}