Abstract
Existing systems to acquire knowledge from expository texts do not perform any learning beyond interpreting the contents of the text. The opportunity to learn from examples included in texts is not exploited. This is a needless limitation because examples in texts are usually show the reader how to integrate the declarative part of the text into an operational concept or procedure. Explanation-based Learning (EBL) seems to fill this gap as it explains the example within the domain theory, generalizes the explanation and operationalizes the concept definition by compiling necessary knowledge from the domain theory into the definition. In this paper, we study the synergistic combination of automatic text analysis and EBL. EBL is used realistically, where the domain theory and the training examples are obtained from a specification or a regulation by a text analysis program, rather than being given a priori. We present a prototype system which demonstrates the potential of this approach. The paper includes a detailed example using the Canadian Income Tax Guide.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Austin (1990) — Proc. of the 7th International Conference on Machine Learning.
Bruce, B. (1975), “Case Systems for Natural Language”, Artificial Intelligence, 6, 327–360.
Cohen, W.W. (1990), “Learning from Textbook Knowledge: A Case Study”, Proc. of AAAI-90, 743–748.
Copeck, T., Delisle, S. & Szpakowicz, S. (1990), “Intelligent Case Analysis in the KATE System”, TR-90-24, Department of Computer Science, University of Ottawa.
DeJong, G.F. & Mooney, R. (1986), “Explanation-Based Learning: An Alternative View”, Machine Learning, 1, 145–176.
Delisle, S. (1987), “A Natural Language Interface for an Expert Advisor System”, M.C.S. Thesis, Department of Computer Science, University of Ottawa.
Delisle, S. (1990), “A Parser for Processing Technical Texts with a Large Coverage of English”, TR-90-25, Department of Computer Science, University of Ottawa.
Dietterich, T.G. (1989), “Machine Learning”, Annual Review of Computer Science, 4, 1989–1990, 255–306.
Ellman, T. (1989), “Explanation-Based Learning: A Survey of Programs and Perspectives”, ACM Computing Surveys, 21, June 1989.
Fong, S. & Berwick, R.C. (1985), “New Approaches to Parsing Conjunctions Using Prolog”, in Proc. of the 23rd Annual Meeting of the ACL, 118–126.
Frey, W., Reyle, U. & Rohrer, C. (1983), “Automatic Construction of a Knowledge Base by Analyzing Texts in Natural Language”, in Proc. of IJCAI-83, 727–729.
Friedman, C. (1986), “Automatic Structures of Sublanguage Information”, in Analyzing Language in Restricted Domains: Sublanguage Description and Processing (edited by R. Grishman and R. Kittredge), LEA, 85–102.
General Tax Guide and Return — Residents of Quebec, 1989, Revenue Canada (Taxation).
Gomez, F. (1989), “Knowledge Acquisition from Natural Language for Expert Systems Based on Classification Problem-Solving Methods”, Proc. of the 4th Knowledge Acquisition for Knowledge-Based Systems Workshop.
Kedar-Cabelli, S.T. & McCarty, L.T. (1987), “Explanation-Based Generalization as Resolution Theorem Proving”, Proc. of the 4th International Workshop on Machine Learning, 383–389
Lenat, D., Guha, R.V., Pittman, K., Pratt, D. & Shepherd, M. (1990), “CYC: Toward Programs with Common Sense”, CACM, 33(8), 30–49.
Mitchell, T., Keller, R.M. & Kedar-Cabelli (1986), S.T., “Explanation-Based Generalization: A Unifying View”, Machine Learning, 1, 47–80.
Moulin, B. & Rousseau, D. (1990), “A Knowledge Acquisition System for Analyzing Prescriptive Texts”, Proc. of the 5th AAAI-Sponsored Knowledge Acquisition for Knowledge-Based Systems Workshop, 22.1–22.20.
Nishida, F., Takamatsu, S., Tani, T. & Kusaka, H. (1986), “Text Analysis and Knowledge Extraction”, Proc. of COLING-86, 241–243.
Regoczei, S. & Hirst, G. (1989), “Sortal Analysis with Sortal, a software assistant for Knowledge Acquisition”, Proc. of the 4th Knowledge Acquisition for Knowledge-Based Systems Workshop.
Reimer, U. (1990), “Automatic Knowledge Acquisition from Texts: Learning Terminological Knowledge via Text Understanding and Inductive Generalization”, Proc. of the 5th AAAI-Sponsored Knowledge Acquisition for Knowledge-Based Systems Workshop, 27.1–27.16.
Rinaldo, F.J. (1989), “Deriving Rules for Medical Expert Systems Using Natural Language Parsing and Discourse Analysis”, Ph.D. Thesis, Computer Science Department, Illinois Institute of Technology.
Sager, N. (1981), Natural Language Information Processing: A Computer Grammar of English and its Applications, Addison-Wesley.
Salembier, M., Matwin S. & d'Alche F. (1990), “Explanation-Based Learning of Disjunctive Concepts with Non-Horn Clauses”, ISMIS '90, To appear.
Silvestro, K. (1988), “Using Explanations for Knowledge-Base Acquisition”, Int. J. Man-Machine Studies 29, 159–169.
Somers, H.L. (1987), Valency and Case in Computational Linguistics, Edinburgh University Press.
Szpakowicz, S. (1990), “Semi-Automatic Acquisition of Conceptual Structures from Technical Texts”, Int. J. Man-Machine Studies, 33, 385–397.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Delisle, S., Matwin, S., Wang, J., Zupan, L. (1991). Explanation-based learning helps acquire knowledge from natural language texts. In: Ras, Z.W., Zemankova, M. (eds) Methodologies for Intelligent Systems. ISMIS 1991. Lecture Notes in Computer Science, vol 542. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-54563-8_96
Download citation
DOI: https://doi.org/10.1007/3-540-54563-8_96
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54563-7
Online ISBN: 978-3-540-38466-3
eBook Packages: Springer Book Archive