NN approaches to natural language: Context and trends

Anton Nijholt

doi:10.1007/978-1-4471-2063-6_76

NN approaches to natural language: Context and trends

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

Abstract

This is a short introduction to topics and problems in natural language processing that are of interest for connectionist research. We recall the natural language processing (NLP) problem and conclude that until now no promising approaches from a neural network (NN) point of view are available. It does not mean that there is no progress in this field. Rather than attacking the complete problem it has become customary to search for subtasks for which a NN approach is useful. In addition, the sometimes rather ad hoc and exotic approaches to language analysis have been replaced by fundamental research into sequence recognition, finite state automata (FSA) simulation and general research on grammatical inference with NNs. We do not confine ourselves to NN approaches, but survey a range of approaches to NLP and provide the framework in which connectionist NLP can be embedded and evaluated.

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	323-330
Number of pages	8
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_76
Publication status	Published - 13 Sept 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

HMI-CI: Computational Intelligence
Natural language processing
Neural network approach
Parse tree
Word sense disambiguation
Finite state automaton

Access to Document

10.1007/978-1-4471-2063-6_76

NN approaches to natural language: Context and Trends
Anton Nijholt (Speaker)
14 Sept 1993
Activity: Talk or presentation › Oral presentation

Cite this

@inproceedings{c12fd1f0cc7b41c2bcc17852198e4832,

title = "NN approaches to natural language: Context and trends",

abstract = "This is a short introduction to topics and problems in natural language processing that are of interest for connectionist research. We recall the natural language processing (NLP) problem and conclude that until now no promising approaches from a neural network (NN) point of view are available. It does not mean that there is no progress in this field. Rather than attacking the complete problem it has become customary to search for subtasks for which a NN approach is useful. In addition, the sometimes rather ad hoc and exotic approaches to language analysis have been replaced by fundamental research into sequence recognition, finite state automata (FSA) simulation and general research on grammatical inference with NNs. We do not confine ourselves to NN approaches, but survey a range of approaches to NLP and provide the framework in which connectionist NLP can be embedded and evaluated.",

keywords = "HMI-CI: Computational Intelligence, Natural language processing, Neural network approach, Parse tree, Word sense disambiguation, Finite state automaton",

author = "Anton Nijholt",

year = "1993",

month = sep,

day = "13",

doi = "10.1007/978-1-4471-2063-6_76",

language = "English",

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

pages = "323--330",

editor = "Stan Gielen and Bert Kappen",

booktitle = "ICANN {\textquoteright}93",

publisher = "Springer",

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

}

Nijholt, A 1993, NN approaches to natural language: Context and trends. 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. 323-330, International Conference on Artificial Neural Networks, ICANN 1993, Amsterdam, Netherlands, 13/09/93. https://doi.org/10.1007/978-1-4471-2063-6_76

NN approaches to natural language: Context and trends. / Nijholt, Anton.
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. 323-330.

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

TY - GEN

T1 - NN approaches to natural language

T2 - International Conference on Artificial Neural Networks, ICANN 1993

AU - Nijholt, Anton

PY - 1993/9/13

Y1 - 1993/9/13

N2 - This is a short introduction to topics and problems in natural language processing that are of interest for connectionist research. We recall the natural language processing (NLP) problem and conclude that until now no promising approaches from a neural network (NN) point of view are available. It does not mean that there is no progress in this field. Rather than attacking the complete problem it has become customary to search for subtasks for which a NN approach is useful. In addition, the sometimes rather ad hoc and exotic approaches to language analysis have been replaced by fundamental research into sequence recognition, finite state automata (FSA) simulation and general research on grammatical inference with NNs. We do not confine ourselves to NN approaches, but survey a range of approaches to NLP and provide the framework in which connectionist NLP can be embedded and evaluated.

AB - This is a short introduction to topics and problems in natural language processing that are of interest for connectionist research. We recall the natural language processing (NLP) problem and conclude that until now no promising approaches from a neural network (NN) point of view are available. It does not mean that there is no progress in this field. Rather than attacking the complete problem it has become customary to search for subtasks for which a NN approach is useful. In addition, the sometimes rather ad hoc and exotic approaches to language analysis have been replaced by fundamental research into sequence recognition, finite state automata (FSA) simulation and general research on grammatical inference with NNs. We do not confine ourselves to NN approaches, but survey a range of approaches to NLP and provide the framework in which connectionist NLP can be embedded and evaluated.

KW - HMI-CI: Computational Intelligence

KW - Natural language processing

KW - Neural network approach

KW - Parse tree

KW - Word sense disambiguation

KW - Finite state automaton

U2 - 10.1007/978-1-4471-2063-6_76

DO - 10.1007/978-1-4471-2063-6_76

M3 - Conference contribution

SN - 978-3-540-19839-0

SP - 323

EP - 330

BT - ICANN ’93

A2 - Gielen, Stan

A2 - Kappen, Bert

PB - Springer

CY - London

Y2 - 13 September 1993 through 16 September 1993

ER -

NN approaches to natural language: Context and trends

Abstract

Conference

Keywords

Access to Document

Fingerprint

Activities

NN approaches to natural language: Context and Trends

Cite this