Hopfield Models as Nondeterministic Finite-state Machines

M.F.J. Drossaers

doi:10.3115/992066.992087

Hopfield Models as Nondeterministic Finite-state Machines

M.F.J. Drossaers

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

49 Downloads (Pure)

Abstract

The use of neural networks for integrated linguistic analysis may be profitable. This paper presents the first results of our research on that subject: a Hopfield model for syntactical analysis. We construct a neural network as an implementation of a bounded push-down automaton, which can accept context-free languages with limited center-embedding. The network's behavior can be predicted a priori, so the presented theory can be tested. The operation of the network as an implementation of the acceptor is provably correct. Furthermore we found a solution to the problem of spurious states in Hopfield models: we use them as dynamically constructed representations of sets of states of the implemented acceptor. The so-called neural-network acceptor we propose, is fast but large.

Original language	English
Title of host publication	COLING-92
Subtitle of host publication	Proceedings of the fifteenth International Conference on Computational Linguistics
Editors	Ch. Boitet
Publisher	Association for Computing Machinery (ACM)
Pages	113-119
Number of pages	7
DOIs	https://doi.org/10.3115/992066.992087
Publication status	Published - 23 Jul 1992
Event	14th International Conference on Computational Linguistics, COLING 1992 - Nantes, France Duration: 23 Aug 1992 → 28 Aug 1992 Conference number: 14

Conference

Conference	14th International Conference on Computational Linguistics, COLING 1992
Abbreviated title	COLING
Country/Territory	France
City	Nantes
Period	23/08/92 → 28/08/92

Access to Document

10.3115/992066.992087

Drossaers1992hopfieldFinal published version, 443 KB

Cite this

@inproceedings{b366b96f9e9d46d9b03154180bb4134d,

title = "Hopfield Models as Nondeterministic Finite-state Machines",

abstract = "The use of neural networks for integrated linguistic analysis may be profitable. This paper presents the first results of our research on that subject: a Hopfield model for syntactical analysis. We construct a neural network as an implementation of a bounded push-down automaton, which can accept context-free languages with limited center-embedding. The network's behavior can be predicted a priori, so the presented theory can be tested. The operation of the network as an implementation of the acceptor is provably correct. Furthermore we found a solution to the problem of spurious states in Hopfield models: we use them as dynamically constructed representations of sets of states of the implemented acceptor. The so-called neural-network acceptor we propose, is fast but large.",

author = "M.F.J. Drossaers",

year = "1992",

month = jul,

day = "23",

doi = "10.3115/992066.992087",

language = "English",

pages = "113--119",

editor = "Ch. Boitet",

booktitle = "COLING-92",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

note = "14th International Conference on Computational Linguistics, COLING 1992, COLING ; Conference date: 23-08-1992 Through 28-08-1992",

}

Drossaers, MFJ 1992, Hopfield Models as Nondeterministic Finite-state Machines. in C Boitet (ed.), COLING-92: Proceedings of the fifteenth International Conference on Computational Linguistics. Association for Computing Machinery (ACM), pp. 113-119, 14th International Conference on Computational Linguistics, COLING 1992, Nantes, France, 23/08/92. https://doi.org/10.3115/992066.992087

Hopfield Models as Nondeterministic Finite-state Machines. / Drossaers, M.F.J.

COLING-92: Proceedings of the fifteenth International Conference on Computational Linguistics. ed. / Ch. Boitet. Association for Computing Machinery (ACM), 1992. p. 113-119.

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

TY - GEN

T1 - Hopfield Models as Nondeterministic Finite-state Machines

AU - Drossaers, M.F.J.

N1 - Conference code: 14

PY - 1992/7/23

Y1 - 1992/7/23

N2 - The use of neural networks for integrated linguistic analysis may be profitable. This paper presents the first results of our research on that subject: a Hopfield model for syntactical analysis. We construct a neural network as an implementation of a bounded push-down automaton, which can accept context-free languages with limited center-embedding. The network's behavior can be predicted a priori, so the presented theory can be tested. The operation of the network as an implementation of the acceptor is provably correct. Furthermore we found a solution to the problem of spurious states in Hopfield models: we use them as dynamically constructed representations of sets of states of the implemented acceptor. The so-called neural-network acceptor we propose, is fast but large.

AB - The use of neural networks for integrated linguistic analysis may be profitable. This paper presents the first results of our research on that subject: a Hopfield model for syntactical analysis. We construct a neural network as an implementation of a bounded push-down automaton, which can accept context-free languages with limited center-embedding. The network's behavior can be predicted a priori, so the presented theory can be tested. The operation of the network as an implementation of the acceptor is provably correct. Furthermore we found a solution to the problem of spurious states in Hopfield models: we use them as dynamically constructed representations of sets of states of the implemented acceptor. The so-called neural-network acceptor we propose, is fast but large.

U2 - 10.3115/992066.992087

DO - 10.3115/992066.992087

M3 - Conference contribution

SP - 113

EP - 119

BT - COLING-92

A2 - Boitet, Ch.

PB - Association for Computing Machinery (ACM)

T2 - 14th International Conference on Computational Linguistics, COLING 1992

Y2 - 23 August 1992 through 28 August 1992

ER -

Hopfield Models as Nondeterministic Finite-state Machines

Abstract

Conference

Access to Document

Fingerprint

Cite this