Natural Language Processing with Modular PDP Networks and Distributed Lexicon

Natural Language Processing with Modular PDP Networks and Distributed Lexicon (1991)

Cached

Download Links

[unlser1.unl.csi.cuny.edu]
[www.cs.utexas.edu]

Other Repositories/Bibliography

DBLP

by Risto Miikkulainen , Michael G. Dyer

Venue:	Cognitive Science
Citations:	77 - 13 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Natural Language Processing with Modular PDP Networks and Distributed Lexicon	user correction - Legacy Corrections
AUTHOR NAME	Risto Miikkulainen	SVM HeaderParse 0.1
AUTHOR AFFIL	University of California, Los Angeles	SVM HeaderParse 0.2
AUTHOR NAME	Michael G. Dyer	SVM HeaderParse 0.1
AUTHOR AFFIL	University of California, Los Angeles	SVM HeaderParse 0.2
ABSTRACT	An approach to connectionist natural language processing is proposed, which is based on hierarchically organized modular Parallel Distributed Processing (PDP) networks and a central lexicon of distributed input/output representations. The modules communicate using these representations, which are global and publicly available in the system. The representations are developed automatically by all networks while they are learning their processing tasks. The resulting representations reflect the regularities in the subtasks, which facilitates robust processing in the face of noise and damage, supports improved generalization, and provides expectations about possible contexts. The lexicon can be extended by cloning new instances of the items, that is, by generating a number of items with known processing properties and distinct identities. This technique combinatorially increases the processing power of the system. The recurrent FGREP module, together with a central lexicon, is used as a ba...	user correction - Legacy Corrections
YEAR	1991	INFERENCE
VENUE	Cognitive Science	INFERENCE
VENUE TYPE	JOURNAL	INFERENCE
PAGES	343--399	INFERENCE
VOLUME	15	INFERENCE
CITATIONS	62 found	ParsCit 1.0