Stacked dependency networks for layout document structuring

ABSTRACT

We address the problems of structuring and annotation of layout-oriented documents. We model the annotation problems as the collective classification on graph-like structures with typed instances and links that capture the domain-specific knowledge. We use the relational dependency networks (RDNs) for the collective inference on the multi-typed graphs. We then describe a variant of RDNs where a stacked approximation replaces the Gibbs sampling in order to accelerate the inference. We report results of evaluation tests for both the Gibbs sampling and stacking inference on two document structuring examples.

REFERENCES

• 1: Crf++: http://chasen.org/taku/software/crf++/.
• 2: Adam L. Berger , Vincent J. Della Pietra , Stephen A. Della Pietra, A maximum entropy approach to natural language processing, Computational Linguistics, v.22 n.1, p.39-71, March 1996
• 3: Christopher M. Bishop, Pattern Recognition and Machine Learning (Information Science and Statistics), Springer-Verlag New York, Inc., Secaucus, NJ, 2006
• 4: Hervé Déjean , Jean-Luc Meunier, Structuring documents according to their table of contents, Proceedings of the 2005 ACM symposium on Document engineering, November 02-04, 2005, Bristol, United Kingdom [doi>10.1145/1096601.1096605]
• 5: Shaolei Feng , R. Manmatha , Andrew McCallum, Exploring the Use of Conditional Random Field Models and HMMs for Historical Handwritten Document Recognition, Proceedings of the Second International Conference on Document Image Analysis for Libraries, p.30-37, April 27-28, 2006 [doi>10.1109/DIAL.2006.19]
• 6: Claus S. Jensen , Uffe Kjærulff , Augustine Kong, Blocking Gibbs sampling in very large probabilistic expert systems, International Journal of Human-Computer Studies, v.42 n.6, p.647-666, June 1995 [doi>10.1006/ijhc.1995.1029]
• 7: G. E. Kopec , P. A. Chou, Document Image Decoding Using Markov Source Models, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.16 n.6, p.602-617, June 1994 [doi>10.1109/34.295905]
• 8: Z. Kou and W. Cohen. Stacked graphical models for efficient inference in Markov random fields. In Proc. SIAM Data Mining, 2007.
• 9: John D. Lafferty , Andrew McCallum , Fernando C. N. Pereira, Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data, Proceedings of the Eighteenth International Conference on Machine Learning, p.282-289, June 28-July 01, 2001
• 10: Percy Liang , Mukund Narasimhan , Michael Shilman , Paul Viola, Efficient Geometric Algorithms for Parsing in Two Dimensions, Proceedings of the Eighth International Conference on Document Analysis and Recognition, p.1172-1177, August 31-September 01, 2005 [doi>10.1109/ICDAR.2005.98]
• 11: S. Mao, A. Rosenfeld, and T. Kanungo. Document structure analysis algorithms: a literature survey. In Proc. SPIE Electronic Imaging, Vol. 5010, page 197, 2003.
• 12: Jennifer Neville , David Jensen, Relational Dependency Networks, The Journal of Machine Learning Research, 8, p.653-692, 5/1/2007
• 13: S. Shetty, H. Srinivasan, M. Beal, et al. Segmentation and labeling of documents using Conditional Random Fields. In Proceedings of SPIE, 2007.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning

Additional Classification:
  I. Computing Methodologies
  I.7 DOCUMENT AND TEXT PROCESSING
      I.7.2 Document Preparation
      I.7.5 Document Capture
          Subjects: Document analysis

General Terms:
Algorithms, Documentation

Keywords:
dependency networks, document structuring, evaluation, stacking