A parser based on connectionist model

Authors:
Hiroshi Nakagawa;Tatsunori Mori
Affiliations:
Yokohama National University, Yokohama, Japan;Yokohama National University, Yokohama, Japan
Venue:
COLING '88 Proceedings of the 12th conference on Computational linguistics - Volume 2
Year:
1988

Citing 6
Cited 1

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
The programmable blackboard model of reading

Parallel distributed processing
Mechanisms of sentence processing: assigning roles to constituents

Parallel distributed processing
Theory of Syntactic Recognition for Natural Languages

Theory of Syntactic Recognition for Natural Languages
A connectionist model of some aspects of anaphor resolution

ACL '84 Proceedings of the 10th International Conference on Computational Linguistics and 22nd annual meeting on Association for Computational Linguistics
On parsing preferences

ACL '84 Proceedings of the 10th International Conference on Computational Linguistics and 22nd annual meeting on Association for Computational Linguistics

Hopfield models as nondeterministic finite-state machines

COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a parser based fully upon the connectionist model(called "CM parser" here after). In order to realize the CM parser, we use Sigma-Pi-Units to implement a constraint of grammatical category order or word order, and a copy mechanism of sub-parse trees. Further more, we suppose there exist weak suppressive connection links between every pair of CM units. By these suppressive links, our CM parser explains why garden path sentences and/or deeply nested sentences are hard to recognize. Our CM parser also explains the preference principles for syntactically ambiguous sentences.