Abstract
Typographic and visual information is an integral part of textual documents. Most information extraction (IE) systems ignore most of this visual information, processing the text as a linear sequence of words. Thus, much valuable information is lost. In this paper, we show how to make use of this visual information for IE. We present an algorithm that allows to automatically extract specific fields of the document (such as the title, author, etc.) based exclusively on the visual formatting of the document, without any reference to the semantic content. The algorithm employs a machine learning approach, whereby the system is first provided with a set of training documents in which the target fields are manually tagged and automatically learns how to extract these fields in future documents. We implemented the algorithm in a system for automatic analysis of documents in PDF format. We present experimental results of applying the system on a set of financial documents, extracting nine different target fields. Overall, the system achieved a 90% accuracy.
Similar content being viewed by others
References
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
Proceedings of the third message understanding conference (MUC-3) (1991) Morgan Kaufmann
Proceedings of the forth message understanding conference (MUC-4) (1992) Morgan Kaufmann
Proceedings of the fifth message understanding conference (MUC-5) (1993) Morgan Kaufmann
Proceedings of the sixth message understanding conference (MUC-6) (1995) Morgan Kaufmann
Altamura O, Esposito F, Malerba D (2001) Transforming paper documents into XML format with WISDOM ++ . Int J Document Anal Recog 4(1):2–17
Anjewierden A. AIDAS: incremental logical structure discovery in pdf documents. In: Proceedings of the sixth international conference on document analysis and recognition (ICDAR), pp 374–378
Ashish N, Knoblock C (1997) Wrapper generation for semi-structured internet sources. In: Proceedings of the workshop on management of semistructured data, Tucson
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 179–190
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):83–97
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 328–334
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)
Eikvil L (1999) Information extraction from world wide web – a survey. Technical Report 945, Norweigan Computing Center
Esposito F, Malerba D, Lisi FA (2000) Machine learning for intelligent processing of printed documents. J Intell Inform Syst 14(2/3):178–198
Etzioni O, Weld D (1994) A softbot-based interface to the internet. Commun ACM 37(7):72–76
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 404–408
Friedman M, Weld DS (1997) Efficiently executing information-gathering plans. In: 15th international joint conference on artificial intelligence, Nagoya, Japan, pp 785–791
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 1007–1015
Hammer J, Garcıa-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 532–535
Hsu CN, Dung MT (1998) Generating finite-state transducers for semi-structured data extraction from the web. Inform Syst 23(8):521–538
Kushmerick N (2000) Wrapper induction: Efficiency and expressiveness. Artif Intell 118(1–2):15–68
Lewis JW (1991) Wrappers: integration utilities and services for the DICE architecture. In: Proceedings of the second national symposium on concurrent engineering, pp 445–457
Lovegrove WS, Brailsford DF (1995) Document analysis of PDF files: methods, results and implications. Electron Publish 8(2/3):207–220
Muslea I, Minton S, Knoblock CA (2001) Hierarchical wrapper induction for semistructured information sources. Autonom Agents Multi-Agent Syst 4(1/2):93–114
Papageorgiou C, Poggio T (2000) A trainable system for object detection. Int J Comput Vis 38(1):15–33
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 319–344
Poggio T, Edelman S (1990) Network that learns to recognize 3D objects. Nature 343:263–266
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 203–210
Selberg E, Etzioni O (1997) The MetaCrawler architecture for resource aggregation on the Web. IEEE Expert 12(1):8–14
Soderland S (1999) Learning information extraction rules for semi-structured and free text. Mach Learn 34(1–3):233–272
Author information
Authors and Affiliations
Corresponding author
Additional information
A preliminary description of this work appeared in [28].
Rights and permissions
About this article
Cite this article
Aumann, Y., Feldman, R., Liberzon, Y. et al. Visual information extraction. Knowl Inf Syst 10, 1–15 (2006). https://doi.org/10.1007/s10115-006-0014-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-006-0014-x