Abstract
The two previous papers have presented quite different opinions on how connectionism can be best used in natural language processing. I would like to follow up on van Gelder’s suggestion of a radical view of connectionist language modeling, albeit under some preconditions, and briefly present the approach undertaken at the Austrian Research Institute of Artificial Intelligence (ARAI). I will also discuss some consequences of this approach and comment on Schnelle’s suggestions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dorffner G.: A Step Toward Sub—Symbolic Language Models without Linguistic Representations, in Reilly R., Sharkey N.(eds.): Connectionist Approaches to Language Processing (Vol. I), Lawrence Erlbaum (in press).
Elman J.L.: Finding Structure in Time, UCSD, CRL Technical Report 8801, 1988.
Smolensky P.: On the Proper Treatment of Connectionism, Behavioral and Brain Sciences 11 (88), p. 1–74, 1988.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dorffner, G. (1990). A Radical View on Connectionist Language Modeling. In: Dorffner, G. (eds) Konnektionismus in Artificial Intelligence und Kognitionsforschung. Informatik-Fachberichte, vol 252. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76070-9_26
Download citation
DOI: https://doi.org/10.1007/978-3-642-76070-9_26
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-53131-9
Online ISBN: 978-3-642-76070-9
eBook Packages: Springer Book Archive