Abstract
We discuss a new framework for text understanding. Three major design decisions characterize this approach. First, we take the problem of text understanding to be a particular case of the general problem of abductive inference. Second, we use probability theory to handle the uncertainty which arises in this abductive inference process. Finally, all aspects of natural language processing are treated in the same framework, allowing us to integrate syntactic, semantic and pragmatic constraints. In order to apply probability theory to this problem, we have developed a probabilistic model of text understanding. To make it practical to use this model, we have devised a way of incrementally constructing and evaluating belief networks. We have written a program,wimp3, to experiment with this framework. To evaluate this program, we have developed a simple ‘single-blind’ testing method.
Similar content being viewed by others
References
Carroll, G. and Charniak, E. (1989) Finding plans with a marker-passer, inProceedings of the Plan-recognition Workshop.
Charniak, E. (1986) A neat theory of marker passing, inProceedings of the Fifth National Conference on Artificial Intelligence, pp. 584–589.
Charniak, E. and Goldman, R. P. (1988) A logic for semantic interpretation, inProceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 87–94.
Charniak, E. and Goldman, R. P. (1989) A semantics for probabilistic quantifier-free first-order languages, with particular application to story understanding, inProceedings of the 11th International Joint Conference on Artificial Intelligence, pp. 1074–1079.
Charniak, E. and Goldman, R. P. (1990) Plan recognition in stories and in life, inUncertainty in Artificial Intelligence 5, Henrion, M., Schachter, R. D., Kanal, L. N. and Lemmer, J. F. (eds). North-Holland, Amsterdam.
Charniak, E. and Goldman, R. P. (1991) Probabilistic abduction for plan-recognition. Technical Report CS-91-12, Brown University Computer Science Department, Providence, RI.
Charniak, E. and McDermott, D. (1985)Introduction to Artificial Intelligence, Addison-Wesley, Reading, MA.
Chin, H. L. and Cooper, G. F. (1987) Stochastic simulation of Bayesian belief networks, inProceedings of the Workshop on Uncertainty and Probability in Artificial Intelligence, pp. 106–113.
Cooper, G. F. (1987) Probabilistic inference using belief networks is NP-hard. Technical Report KSL-87-27, Medical Computer Science Group, Stanford University.
Cox, R. T. (1946) Probability frequency and reasonable expectation.American Journal of Physics,14, 1–13.
Cullingford, R. E. (1978) Script application: computer understanding of newspaper stories. Technical Report, Department of Computer Science, Yale University, New Haven, CT.
D'Ambrosio, B. (1988a) A hybrid approach to reasoning under uncertainty.International Journal of Approximate Reasoning 2, 29–45.
D'Ambrosio, B. (1988b) Process, structure and modularity in reasoning with uncertainty, inThe Fourth Workshop on Uncertainty in Artificial Intelligence, pp. 64–72.
deKleer, J. (1986) An assumption-based TMS.Artificial Intelligence,28, 127–162.
Goldman, R. P. (1990) A probabilistic approach to language understanding. Technical Report CS-90-34, Computer Science Department, Brown University.
Goldman, R. P. and Charniak, E. (1990) Dynamic construction of belief networks, inProceedings of the Sixth Conference on Uncertainty in Artificial Intelligence, pp. 90–97.
Grosz, B. J. and Sidner, C. (1986) Attention, intention and the structure of discourse.Computational Linguistics,12.
Hobbs, J. R. and Martin, P. (1987) Local pragmatics, inProceedings of the 10th International Joint Conference on Artificial Intelligence, pp. 520–523.
Hobbs, J. R., Stickel, M., Martin, P. and Edwards, D. (1988) Interpretation as abduction, inProceedings of the 26th Annual Meeting of the ACL, pp. 95–103.
Jensen, F. V. (1990) Bayesian updating in recursive graphical models by local computations. Technical Report R 89-15, Institute for Electornic Systems, Department of Mathematics and Computer Science, University of Aalborg, Aalborg, Denmark.
Kjærulff, U. (1990) Triangulations of graphs—algorithms giving small total clique size. Technical Report R 90-09, Institute for Electronic Systems, Department of Mathematics and Computer Science, University of Aalborg, Aalborg, Denmark.
Laskey, K. B. and Lehner, P. E. (1988) Belief maintenance: an integrated approach to uncertainty management, inProceedings of the Seventh National Conference on Artificial Intelligence, pp. 210–214.
Lauritzen, S. L. and Spiegelhalter, D. J. (1988) Local computations with probabilities on graphical structures and their application to expert systems.Journal of the Royal Statistical Society,50, 157–224.
Nilsson, N. (1986) Probabilistic logic.Artificial Intelligence,28, 71–88.
Norvig, P. (1987) Inference in text understanding, inProceedings of the Sixth National Conference on Artificial Intelligence, pp. 561–565.
Palmer, M. and Finin, T. (1990) Workshop on the evaluation of natural language processing systems.Computational Linguistics 16, 175–181.
Pearl, J. (1988)Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, Morgan Kaufmann, Los Altos, CA.
Shimony, S. and Charniak, E. (1990) A new algorithm for finding map assignments to belief networks, inProceedings of the Sixth Conference on Uncertainty in Artificial Intelligence, pp. 98–103.
Srinivas, S. and Breese, J. (1989)IDEAL: Influence Diagram Evaluation and Analysis in Lisp, Rockwell International Science Center, Palo Alto, CA.
Webber, B. L. (1987) The interpretation of tense in discourse, inProceedings of the 25th Annual Meeting of the ACL, pp. 147–154.
Wilensky, R. (1983)Planning and Understanding, Addison-Wesley, Reading, MA.
Wong, D. (1981) Language comprehension in a problem solver, inProceedings of the 4th International Joint Conference on Artificial Intelligence, pp. 7–12.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Goldman, R.P., Charniak, E. Probabilistic text understanding. Stat Comput 2, 105–114 (1992). https://doi.org/10.1007/BF01889589
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/BF01889589