Abstract
Overgeneralization is a major issue in the identification of grammars for formal languages from positive data. Different formulations of generalization and specialization strategies have been proposed to address this problem, and recently there has been a flurry of activity investigating such strategies in the context of indexed families of recursive languages. The present paper studies the power of these strategies to learn recursively enumerable languages from positive data. In particular, the power of strong-monotonic, monotonic, and weak-monotonic (together with their dual notions modeling specialization) strategies are investigated for identification of r.e. languages. These investigations turn out to be different from the previous investigations on learning indexed families of recursive languages and at times require new proof techniques. A complete picture is provided for the relative power of each of the strategies considered. An interesting consequence is that the power of weak-monotonic strategies is equivalent to that of conservative strategies. This result parallels the scenario for indexed classes of recursive languages. It is also shown that any identifiable collection of r.e. languages can also be identified by a strategy that exhibits the dual of weak-monotonic property. An immediate consequence of the proof of this result is that if attention is restricted to infinite r.e. languages, then conservative strategies can identify every identifiable collection.
Similar content being viewed by others
References
D. Angluin, Inductive inference of formal languages from positive data, Information and Control 45 (1980) 117–135.
L. Blum and M. Blum, Toward a mathematical theory of inductive inference, Information and Control 28 (1975) 125–155.
M. Blum, A machine independent theory of the complexity of recursive functions, Journal of the ACM 14 (1967) 322–336.
M. Fulk, Prudence and other conditions on formal language learning, Information and Computation 85 (1990) 1–11.
E.M. Gold, Language identification in the limit, Information and Control 10 (1967) 447–474.
J. Hopcroft and J. Ullman, Introduction to Automata Theory, Languages, and Computation (Addison-Wesley, Reading, MA, 1979).
S. Jain and A. Sharma, Recursion theoretic characterizations of language learning, Technical Report 281, University of Rochester (1989).
S. Jain and A. Sharma, Characterizing language learning by standardizing operations, Journal of Computer and System Sciences 49(1) (1994) 96–107.
S. Jain and A. Sharma, Characterizing language learning in terms of computable numberings, Annals of Pure and Applied Logic 84(1) (1997) 51–72.
K.P. Jantke, Monotonic and non-monotonic inductive inference, New Generation Computing 8 (1991) 349–360.
S. Kapur, Monotonic language learning, in: Proceedings of the Third Workshop on Algorithmic Learning Theory (JSAI Press, 1992). Proceedings reprinted as Lecture Notes in Artificial Intelligence, Springer-Verlag.
S. Kapur, Uniform characterizations of various kinds of language learning, in: Proceedings of the Fourth International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 744 (Springer, Berlin, 1993).
S. Kapur and G. Bilardi, Language learning without overgeneralization, in: Proceedings of the Ninth Annual Symposium on Theoretical Aspects of Computer Science, Lecture Notes in Computer Science 577 (Springer, New York, 1992).
E. Kinber, Monotonicity versus efficiency for learning languages from texts, Technical Report 94–22, Department of Computer and Information Sciences, University of Delaware (1994).
E. Kinber and F. Stephan, Language learning from texts: Mind changes, limited memory and monotonicity, Information and Computation 123(2) (1995) 224–241.
S. Lange and T. Zeugmann, Monotonic language learning on informant, Technical Report 11/92, GOSLER-Report, FB Mathematik und Informatik, TH Lepzig (1992).
S. Lange and T. Zeugmann, Types of monotonic language learning and their characterization, in: Proceedings of the Fifth Annual Workshop on Computational Learning Theory, Pittsburgh, PA (ACM Press, 1992) pp. 377–390.
S. Lange and T. Zeugmann, Language learning with bounded number of mind changes, in: Proceedings of the Tenth Annual Symposium on Theoretical Aspects of Computer Science, Lecture Notes Computer Science 665 (Springer, New York, 1993) pp. 682–691.
S. Lange and T. Zeugmann, Monotonic versus non-monotonic language learning, in: Proceedings of the Second International Workshop on Nonmonotonic and Inductive Logic, Lecture Notes in Artificial Intelligence 659 (Springer, Berlin, 1993) pp. 254–269.
S. Lange and T. Zeugmann, On the impact of order independence to the learnability of recursive languages, Technical Report ISIS-RR–93–17E, Institute for Social Information Science Research Report, Fujitsu Laboratories Ltd. (1993).
S. Lange, T. Zeugmann and S. Kapur, Class preserving monotonic language learning, Technical Report 14/92, GOSLER-Report, FB Mathematik und Informatik, TH Leipzig (1992).
S. Lange, T. Zeugmann and S. Kapur, Monotonic and dual monotonic language learning, Theoretical Computer Science A 155 (1996) 365–410.
M. Machtey and P. Young, An Introduction to the General Theory of Algorithms (North-Holland, New York, 1978).
S. Muggleton and C. Feng, Efficient induction of logic programs, in: Proceedings of the First Conference on Algorithmic Learning Theory (Ohmsa Publishers, Tokyo, 1990) pp. 368–381. Reprinted by Ohmsa Springer-Verlag.
Y. Mukouchi, Characterization of finite identification, in: Proceedings of the Third International Workshop on Analogical and Inductive Inference, Dagstuhl Castle, Germany, ed. K.P. Jantke (October 1992) pp. 260–267.
Y. Mukouchi, Inductive inference with bounded mind changes, in: Proceedings of the Third Workshop on Algorithmic Learning Theory (JSAI Press, 1992) pp. 125–134. Proceedings reprinted as Lecture Notes in Artificial Intelligence, Springer-Verlag.
Y. Mukouchi and S. Arikawa, Inductive inference machines that can refute hypothesis spaces, in: Proceedings of the Fourth International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 744 (Springer, Berlin, 1993) pp. 123–136.
D. Osherson, M. Stob and S. Weinstein, Learning strategies, Information and Control 53 (1982) 32–51.
D. Osherson, M. Stob and S. Weinstein, Systems that Learn, An Introduction to Learning Theory for Cognitive and Computer Scientists (MIT Press, Cambridge, MA, 1986).
J.R. Quinlan, Learning logical definitions from relations, Machine Learning 5(3) (1990) 239–266.
H. Rogers, Gödel numberings of partial recursive functions, Journal of Symbolic Logic 23 (1958) 331–341.
H. Rogers, Theory of Recursive Functions and Effective Computability (McGraw Hill, New York, 1967). Reprinted, MIT Press, 1987.
E. Shapiro, Inductive inference of theories from facts, Technical Report 192, Computer Science Department, Yale University (1981).
R. Wiehagen, A thesis in inductive inference, in: Nonmonotonic and Inductive Logic, 1st International Workshop, Karlsruhe, Germany, Lecture Notes in Artificial Intelligence 543, eds. P. Schmitt, J. Dix and K. Jantke (Springer, Berlin, 1990) pp. 184–207.
R. Wiehagen and W. Liepe, Charakteristische Eigenschaften von erkennbaren Klassen rekursiver Funktionen, Electronische Informationverarbeitung und Kybernetik 12 (1976) 421–438 (in German).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Jain, S., Sharma, A. Generalization and specialization strategies for learning r.e. languages. Annals of Mathematics and Artificial Intelligence 23, 1–26 (1998). https://doi.org/10.1023/A:1018903922049
Issue Date:
DOI: https://doi.org/10.1023/A:1018903922049