Learnability of Translations from Positive Examples
- Noriko Sugimoto
- … show all 1 hide
Purchase on Springer.com
$29.95 / €24.95 / £19.95*
* Final gross prices may vary according to local VAT.
One of the most important issues in machine translations is deducing unknown rules from pairs of input-output sentences. Since the translations are expressed by elementary formal systems (EFS’s, for short), we formalize learning translations as the process of guessing an unknown EFS from pairs of input-output sentences. In this paper, we propose a class of EFS’s called linearly-moded EFS’s by introducing local variables and linear predicate inequalities based on mode information, which can express translations of context-sensitive languages. We show that, for a given input sentence, the set of all output sentences is finite and computable in a translation defined by a linearly-moded EFS. Finally, we show that the class of translations defined by linearly-moded EFS’s is learnable under the condition that the number of clauses in an EFS and the length of the clause are bounded by some constant.
- A. V. Aho and J. D. Ullman. Properties of syntax directed translations. Journal of Computer and System Sciences 3:319–334, 1969.
- A. V. Aho and J. D. Ullman. Syntax directed translation and the pushdown assembler. Journal of Computer and System Sciences 3:37–56, 1969.
- D. Angluin. Inductive inference of formal languages from positive data. Information and Control 45:117–135, 1980. CrossRef
- D. Angluin. Inference of reversible languages. Journal of the ACM 29:741–765, July 1982.
- S. Arikawa, T. Shinohara, and A. Yamamoto. Learning elementary formal systems. Theoretical Computer Science 95:97–113, 1992. CrossRef
- H. Arimura and T. Shinohara. Inductive inference of prolog programs with linear data dependency from positive data. Proc. Information Modelling and Knowledge Bases V, 1994.
- E. Gold. Language identification in the limit. Information and Control 10:447–474, 1967. CrossRef
- E. Irons. A syntax directed compiler for ALGOL-60. Communications of the ACM 4:51–55, 1961. CrossRef
- P. M. Lewis and R. E. Stearns. Syntax-directed transduction. Journal of the ACM 15:465–488, 1968. CrossRef
- M. K. Rao. A class of prolog programs inferable from positive data. Lecture Notes in Artificial Intelligence 1160, 272–284, 1996.
- T. Shinohara. Inductive inference of monotonic formal systems from positive data. New Generation Computing, 8:371–384, 1991. CrossRef
- T. Shinohara. Rich classes inferable from positive data: length-bounded elementary formal system. Information and Computation 108:175–186, 1994. CrossRef
- R. Smullyan. Theory of formal systems. Princeton Univ. Press, 1961.
- N. Sugimoto, K. Hirata and H. Ishizaka. Constructive learning of translations based on dictionaries. Lecture Notes in Artificial Intelligence 1160, 177–184, 1996.
- A. Yamamoto. Procedural semantics and negative information of elementary formal system. Journal of Logic Programming 13:89–97, 1992. CrossRef
- Learnability of Translations from Positive Examples
- Book Title
- Algorithmic Learning Theory
- Book Subtitle
- 9th International Conference, ALT’98 Otzenhausen, Germany, October 8–10, 1998 Proceedings
- pp 169-178
- Print ISBN
- Online ISBN
- Series Title
- Lecture Notes in Computer Science
- Series Volume
- Series ISSN
- Springer Berlin Heidelberg
- Copyright Holder
- Springer-Verlag Berlin Heidelberg
- Additional Links
- Industry Sectors
- eBook Packages
- Editor Affiliations
- 1. AG Künstliche Intelligenz - Expertensysteme, UniversitÄt Kaiserslautern
- 2. Department of Computer Science, University of Maryland
- 3. AG Algorithmischesn Lernen, UniversitÄt Kaiserslautern
- 4. Graduate School of Information Science and Electrical Engineering Department of Informatics, Kyushu University
- Noriko Sugimoto (5)
- Author Affiliations
- 5. Department of Artificial Intelligence, Kyushu Institute of Technology, Kawazu 680-4, Iizuka, 820-8502, JAPAN
To view the rest of this content please follow the download PDF link above.