Advertisement

Language-Level Syntactic and Semantic Constraints Applied to Visual Word Recognition

  • Jonathan J. Hull
Conference paper
Part of the NATO ASI Series book series (volume 124)

Abstract

Various aspects of using language-level syntactic and semantic constraints to improve the performance of word recognition algorithms are discussed. Following a brief presentation of a hypothesis generation model for handwritten word recognition, various types of language-level constraints are reviewed. Methods that exploit these characteristics are discussed including intra-document word correlation, common vocabularies, part-of-speech tag cooccurrence, structural parsing with a chart data structure, and semantic biasing with a thesaurus.

Keywords

Word Recognition Visual Word Recognition Content Word Function Word Viterbi Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Baird, H. S. and Thompson, K., “Reading Chess,” IEEE Transactions on Pattern Analysis and Machine Intelligence 12 (1990), 552–559.CrossRefGoogle Scholar
  2. 2.
    Cherkassky, V., Rao, M., Weschler, H., Bahl, L. R., Jelinek, F. and Mercer, R. L., “A maximum likelihood approach to continuous speech recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-5, 2 (March, 1983), 179–190.Google Scholar
  3. 3.
    Chien, L. F., Chen, K. J. and Lee, L. S., “An augmented chart data structure with efficient word lattice parsing scheme in speech recognition applications,” 13th International Conference on Computational Linguistics 2 (1990), 60-65.Google Scholar
  4. 4.
    Church, K., Gale, W., Hanks, P. and Hindle, D., “Parsing, word associations, and typical predicate-argument relations,” International Workshop on Parsing Technologies, Pittsburgh, Pennsylvania, August 28–31, 1989, 389-398.Google Scholar
  5. 5.
    Evett, L. J., Wells, C. J., Keenan, F. G., Rose, T. and Whitrow, R. J., “Using linguistic information to aid handwriting recognition,” in From Pixels to Features III: Frontiers in Handwriting Recognition, S. Impedovo and J. C. Simon (editor), Elsevier Science Publishers B.V., 1992.Google Scholar
  6. 6.
    Forney, G. D.,’ The Viterbi algorithm/’ Proceedings of the IEEE 61, 3 (March, 1973), 268–278.CrossRefMathSciNetGoogle Scholar
  7. 7.
    Francis, W. N. and Kucera, H., Frequency Analysis of English Usage: Lexicon and Grammar, Houghton Mifflin, Co., Boston, Massachusetts, 1982.Google Scholar
  8. 8.
    Hong, T. and Hull, J. J., “A Probabilistic Lattice Chart Parser for Text Recognition,” ICDAR-93: Second IAPR Conference on Document Analysis and Recognition, Tsukuba Science City, Japan, October 20-22, 1993. submitted.Google Scholar
  9. 9.
    Hull, J. J., Srihari, S. N. and Choudhari, R., “An integrated algorithm for text recognition: comparison with a cascaded algorithm,” IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-5, 4 (July, 1983), 384–395.CrossRefGoogle Scholar
  10. 10.
    Hull, J. J., “Inter-word constraints in visual word recognition,” Proceedings of the Conference of the Canadian Society for Computational Studies of Intelligence, Montreal, Canada, May 21–23, 1986, 134-138.Google Scholar
  11. 11.
    Hull, J. J., “Feature selection and language syntax in text recognition,” in From Pixels to Features, J. C. Simon (editor), North Holland, 1989, 249-260.Google Scholar
  12. 12.
    Hull, J. J., Ho, T. K., Favata, J., Govindaraju, V. and Srihari, S. N., “Combination of segmentation-based and wholistic handwritten word recognition algorithms,” From Pixels to Features III: International Workshop on Frontiers in Handwriting Recognition, Bonas, France, September 23–27, 1991, 229-240.Google Scholar
  13. 13.
    Hull, J. J. and Chin, A. T., “Semantic information extraction with a thesaurus for visual word recognition,” in Advances in Structual and Syntactic Pattern Recognition, H. Bunke (editor), World Scientific, 1992, 342-351.Google Scholar
  14. 14.
    Hull, J. J., “A hidden Markov model for language syntax in text reconition,” 11th IAPR International Conference on Pattern Recognition, The Hague, The Netherlands, August 30 — September 3, 1992, 124-127.Google Scholar
  15. 15.
    Hull, J. J. and Li, Y., “Word recognition result interpretation using the vector space model for information retrieval,” Second Annual Symposium on Document Analysis and Information Retrieval, Las Vegas, Nevada, April 26–28, 1993.Google Scholar
  16. 16.
    Jones, M. A., Story, G. A. and Ballard, B. W., “Integrating multiple knowledge sources in a Bayesian OCR post-processor,” First International Conference on Document Analysis and Recognition, Saint-Malo, France, September 30 — October 2, 1991, 925-933.Google Scholar
  17. 17.
    Khoubyari, S. and Hull, J. J., “Keyword location in noisy document images,” Second Annual Symposium on Document Analysis and Information Retrieval, Las Vegas, Nevada, April 26–28, 1993.Google Scholar
  18. 18.
    Kucera, H. and Francis, W. N., Computational analysis of present-day American English, Brown University Press, Providence, Rhode Island, 1967.Google Scholar
  19. 19.
    Kuhn, R., “Speech récognition and the frequency of recently used words: A modified Markov model for natural language,” Proceedings of the 12 th International Conference on Computational Linguistics, Budapest, Hungary, August 22-27, 1988,348-350.Google Scholar
  20. 20.
    Nagy, G., Seth, S. and Einspahr, K., “Decoding substitution ciphers by means of word matching with application to OCR,” IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-9, 5 (September, 1987), 710–715.CrossRefGoogle Scholar
  21. 21.
    Rabiner, L. R. and Huang, B. H., “An introduction to hidden Markov model,” ASSP Magazine 3, 1 (1986), 4–16.CrossRefGoogle Scholar
  22. 22.
    Rose, T. G., Evett, L. J. and Whitrow, R. J., “The use of semantic information as an aid to handwriting recognition,” First International Conference on Document Analysis and Recognition, Saint-Malo, France, September 30 — October 2, 1991, 629-637.Google Scholar
  23. 23.
    Salton, G., Automatic text processing, Addison Wesley, 1988.Google Scholar
  24. 24.
    Salton, G., “Developments in automatic information retrieval,” Science 253 (1991), 974–980.CrossRefMathSciNetGoogle Scholar
  25. 25.
    Seneff, S., “Probabilistic parsing for spoken language applications,” International Workshop on Parsing Technologies, Pittsburgh, Pennsylvania, August 28–31, 1989, 209-218.Google Scholar
  26. 26.
    Tomita, M., “An efficient word lattice parsing algorithm for continuous speech recognition,” Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, 1986, 1569-1572.Google Scholar
  27. 27.
    White, G. M., “Natural language understanding and speech recognition,” Communications of the ACM 33, 8 (August, 1990), 74–82.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Jonathan J. Hull
    • 1
  1. 1.Center of Excellence for Document Analysis and Recognition, Department of Computer ScienceState University of New York at BuffaloBuffaloUSA

Personalised recommendations