An Extended Kohonen Feature Map for Sentence Recognition

Aarnoud Hoekstra; Marc F.J. Drossaers

doi:10.1007/978-1-4471-2063-6_96

An Extended Kohonen Feature Map for Sentence Recognition

Aarnoud Hoekstra, Marc F.J. Drossaers

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

In this paper an extended Kohonen feature map is proposed that is able to store sequences of input patterns. The extended map is used in a natural language application: the recognition of sentences produced by a regular grammar. This network is able to learn to simulate a finite-state machine for the grammar, given examples of legal sentences from the grammar.

Original language	English
Title of host publication	ICANN ’93
Subtitle of host publication	Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993
Editors	Stan Gielen, Bert Kappen
Place of Publication	London
Publisher	Springer
Pages	404-407
ISBN (Electronic)	978-1-4471-2063-6
ISBN (Print)	978-3-540-19839-0
DOIs	https://doi.org/10.1007/978-1-4471-2063-6_96
Publication status	Published - 30 Jan 1993
Event	International Conference on Artificial Neural Networks, ICANN 1993 - Amsterdam, Netherlands Duration: 13 Sept 1993 → 16 Sept 1993

Conference

Conference	International Conference on Artificial Neural Networks, ICANN 1993
Abbreviated title	ICANN
Country/Territory	Netherlands
City	Amsterdam
Period	13/09/93 → 16/09/93

Keywords

Natural language processing
Input pattern
Winning neuron
Natural language processing task
Sentence recognition

Access to Document

10.1007/978-1-4471-2063-6_96

Cite this

@inproceedings{e44e2cbf4bd74b46b2a911377bdf9295,

title = "An Extended Kohonen Feature Map for Sentence Recognition",

abstract = "In this paper an extended Kohonen feature map is proposed that is able to store sequences of input patterns. The extended map is used in a natural language application: the recognition of sentences produced by a regular grammar. This network is able to learn to simulate a finite-state machine for the grammar, given examples of legal sentences from the grammar.",

keywords = "Natural language processing, Input pattern, Winning neuron, Natural language processing task, Sentence recognition",

author = "Aarnoud Hoekstra and Drossaers, \{Marc F.J.\}",

year = "1993",

month = jan,

day = "30",

doi = "10.1007/978-1-4471-2063-6\_96",

language = "English",

isbn = "978-3-540-19839-0",

pages = "404--407",

editor = "Stan Gielen and Bert Kappen",

booktitle = "ICANN {\textquoteright}93",

publisher = "Springer",

address = "Germany",

note = "International Conference on Artificial Neural Networks, ICANN 1993, ICANN ; Conference date: 13-09-1993 Through 16-09-1993",

}

Hoekstra, A & Drossaers, MFJ 1993, An Extended Kohonen Feature Map for Sentence Recognition. in S Gielen & B Kappen (eds), ICANN ’93: Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993. Springer, London, pp. 404-407, International Conference on Artificial Neural Networks, ICANN 1993, Amsterdam, Netherlands, 13/09/93. https://doi.org/10.1007/978-1-4471-2063-6_96

An Extended Kohonen Feature Map for Sentence Recognition. / Hoekstra, Aarnoud; Drossaers, Marc F.J.
ICANN ’93: Proceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993. ed. / Stan Gielen; Bert Kappen. London: Springer, 1993. p. 404-407.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - An Extended Kohonen Feature Map for Sentence Recognition

AU - Hoekstra, Aarnoud

AU - Drossaers, Marc F.J.

PY - 1993/1/30

Y1 - 1993/1/30

N2 - In this paper an extended Kohonen feature map is proposed that is able to store sequences of input patterns. The extended map is used in a natural language application: the recognition of sentences produced by a regular grammar. This network is able to learn to simulate a finite-state machine for the grammar, given examples of legal sentences from the grammar.

AB - In this paper an extended Kohonen feature map is proposed that is able to store sequences of input patterns. The extended map is used in a natural language application: the recognition of sentences produced by a regular grammar. This network is able to learn to simulate a finite-state machine for the grammar, given examples of legal sentences from the grammar.

KW - Natural language processing

KW - Input pattern

KW - Winning neuron

KW - Natural language processing task

KW - Sentence recognition

U2 - 10.1007/978-1-4471-2063-6_96

DO - 10.1007/978-1-4471-2063-6_96

M3 - Conference contribution

SN - 978-3-540-19839-0

SP - 404

EP - 407

BT - ICANN ’93

A2 - Gielen, Stan

A2 - Kappen, Bert

PB - Springer

CY - London

T2 - International Conference on Artificial Neural Networks, ICANN 1993

Y2 - 13 September 1993 through 16 September 1993

ER -

An Extended Kohonen Feature Map for Sentence Recognition

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this