Abstract
A preliminary experimental result is reported on language identification tasks by Recurrent Self-Organization Maps (RSOM) with a context map layer, using English part-of-speech strings of variable length. With subsymbolic processing, RSOM suprasymbolically sublimed syntactic rules into a topological configuration.
The research reported here is partially supported by a 21st COE Program (#J19), granted to Kyushu Institute of Technology, by MEXT, Japan. The standard disclaimers apply.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Gold, E.M.: Language Identification in the Limit. Information and Control 10, 447–474 (1967)
Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mizushima, F., Toyoshima, T. (2006). Suprasymbolic Grammar Induction by Recurrent Self-Organizing Maps. In: Sakakibara, Y., Kobayashi, S., Sato, K., Nishino, T., Tomita, E. (eds) Grammatical Inference: Algorithms and Applications. ICGI 2006. Lecture Notes in Computer Science(), vol 4201. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11872436_31
Download citation
DOI: https://doi.org/10.1007/11872436_31
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-45264-5
Online ISBN: 978-3-540-45265-2
eBook Packages: Computer ScienceComputer Science (R0)