Identification in the limit of categorial grammars

It is proved that for any k, the class of classical categorial grammars that assign at most k types to each symbol in the alphabet is learnable, in the Gold (1967) sense of identification in the limit from positive data. The proof crucially relies on the fact that the concept known as finite elasticity in the inductive inference literature is preserved under the inverse image of a finite-valued relation. The learning algorithm presented here incorporates Buszkowski and Penn's (1990) algorithm for determining categorial grammars from input consisting of functor-argument structures.

[1]  Keith Wright.  Identification of unions of languages drawn from an identifiable class , 1989, COLT '89.

[2]  Aravind K. Joshi,et al.  Skeletal Structural Descriptions , 1978, Inf. Control..

[3]  Mark Steedman,et al.  Dependency and Coordination in the Grammar of Dutch and English , 1985 .

[4]  Noam Chomsky.  Knowledge of language: its nature, origin, and use , 1988 .

[5]  Mark Steedman,et al.  Combinators and Grammars , 1988 .

[6]  W. Buszkowski.  Generative Power of Categorial Grammars , 1988 .

[7]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..

[8]  Makoto Kanazawa.  Learnable Classes of Categorial Grammars , 1998 .

[9]  Umesh V. Vazirani,et al.  An Introduction to Computational Learning Theory , 1994 .

[10]  Noam Chomsky.  Knowledge of Language , 1986 .

[11]  Richard Montague,et al.  The Proper Treatment of Quantification in Ordinary English , 1973 .

[12]  Gerald Penn,et al.  Categorial grammars determined from linguistic data by unification , 1990, Stud Logica.

[13]  Michael J. Maher,et al.  Unification Revisited , 1988, Foundations of Deductive Databases and Logic Programming..

[14]  Yehoshua Bar-Hillel,et al.  Language and Information , 1964 .

[15]  Scott Weinstein,et al.  Formal Learning Theory , 1997, Handbook of Logic and Language.

[16]  Dana Angluin,et al.  Inference of Reversible Languages , 1982, JACM.

[17]  Yehoshua Bar-Hillel.  Some Linguistic Problems Connected with Machine Translation , 1953, Philosophy of Science.

[18]  David R. Dowty.  Type Raising, Functional Composition, and Non-Constituent Conjunction , 1988 .

[19]  Takeshi Shinohara.  Inductive inference from positive data is powerful , 1990, COLT '90.

[20]  Dana Angluin,et al.  Inductive Inference of Formal Languages from Positive Data , 1980, Inf. Control..

[21]  Makoto Kanazawa.  A note on language classes with finite elasticity , 1994 .

[22]  Mark Steedman,et al.  Combinatory grammars and parasitic gaps , 1987 .

[23]  Y. Bar-Hillel.  A Quasi-Arithmetical Notation for Syntactic Description , 1953 .

[24]  S. Kapur.  Computational Learning of Languages , 1992 .

[25]  J. Lambek.  The Mathematics of Sentence Structure , 1958 .

[26]  Daniel N. Osherson,et al.  Systems That Learn: An Introduction to Learning Theory for Cognitive and Computer Scientists , 1990 .

[27]  Yasubumi Sakakibara,et al.  Efficient Learning of Context-Free Grammars from Positive Structural Examples , 1992, Inf. Comput..

[28]  Joachim Lambek,et al.  On the Calculus of Syntactic Types , 1961 .

[29]  Emmon W. Bach,et al.  Categorial Grammars and Natural Language Structures , 1988 .

[30]  Kenneth Wexler,et al.  Formal Principles of Language Acquisition , 1980 .

[31]  Carl H. Smith,et al.  Inductive Inference: Theory and Methods , 1983, CSUR.

[32]  Masako Sato,et al.  Properties of Language Classes with Finite Elasticity , 1995, IEICE Trans. Inf. Syst..

[33]  Dana Angluin,et al.  Finding Patterns Common to a Set of Strings , 1980, J. Comput. Syst. Sci..

[34]  Takeshi Shinohara,et al.  The correct definition of finite elasticity: corrigendum to identification of unions , 1991, COLT '91.