A Concepts-of-Sentences Associative Neural Network

Hitoshi Tanaka, Jingtao Huang, Masafumi Hagiwara

Research output: Contribution to journalArticle

Abstract

This paper proposes a new neural network (the concepts-of-sentences associative neural network, CSANN) which performs memory and recall of sentences represented by a semantic network, as an approach toward natural language processing. The semantic network is represented in terms of the triples representation of concepts. The triples representation of concepts consists of concepts linked by relations in sentences represented by natural language. CSANN handles sentence data, which are difficult to handle since the data size is not unique, by decomposing the data into triples representations of concepts and integrating them into the semantic network format. It is verified by computer simulation that the proposed network can store sentences and recall sentences even if the input information is incomplete. Thus, the effectiveness of the proposed network in natural language processing is demonstrated.

Original languageEnglish
Pages (from-to)43-54
Number of pages12
JournalSystems and Computers in Japan
Volume34
Issue number11
DOIs
Publication statusPublished - 2003 Oct

Fingerprint

Semantics
Neural Networks
Neural networks
Semantic Network
Natural Language
Processing
Data storage equipment
Computer simulation
Concepts
Computer Simulation

Keywords

  • Concept
  • Distributed representation
  • Multiple-winner self-organizing network
  • Natural language
  • Triples representation

ASJC Scopus subject areas

  • Hardware and Architecture
  • Information Systems
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

A Concepts-of-Sentences Associative Neural Network. / Tanaka, Hitoshi; Huang, Jingtao; Hagiwara, Masafumi.

In: Systems and Computers in Japan, Vol. 34, No. 11, 10.2003, p. 43-54.

Research output: Contribution to journalArticle

Tanaka, Hitoshi ; Huang, Jingtao ; Hagiwara, Masafumi. / A Concepts-of-Sentences Associative Neural Network. In: Systems and Computers in Japan. 2003 ; Vol. 34, No. 11. pp. 43-54.
@article{ed6918f8d9da4aefb8a536595040dcda,
title = "A Concepts-of-Sentences Associative Neural Network",
abstract = "This paper proposes a new neural network (the concepts-of-sentences associative neural network, CSANN) which performs memory and recall of sentences represented by a semantic network, as an approach toward natural language processing. The semantic network is represented in terms of the triples representation of concepts. The triples representation of concepts consists of concepts linked by relations in sentences represented by natural language. CSANN handles sentence data, which are difficult to handle since the data size is not unique, by decomposing the data into triples representations of concepts and integrating them into the semantic network format. It is verified by computer simulation that the proposed network can store sentences and recall sentences even if the input information is incomplete. Thus, the effectiveness of the proposed network in natural language processing is demonstrated.",
keywords = "Concept, Distributed representation, Multiple-winner self-organizing network, Natural language, Triples representation",
author = "Hitoshi Tanaka and Jingtao Huang and Masafumi Hagiwara",
year = "2003",
month = "10",
doi = "10.1002/scj.10476",
language = "English",
volume = "34",
pages = "43--54",
journal = "Systems and Computers in Japan",
issn = "0882-1666",
publisher = "John Wiley and Sons Inc.",
number = "11",

}

TY - JOUR

T1 - A Concepts-of-Sentences Associative Neural Network

AU - Tanaka, Hitoshi

AU - Huang, Jingtao

AU - Hagiwara, Masafumi

PY - 2003/10

Y1 - 2003/10

N2 - This paper proposes a new neural network (the concepts-of-sentences associative neural network, CSANN) which performs memory and recall of sentences represented by a semantic network, as an approach toward natural language processing. The semantic network is represented in terms of the triples representation of concepts. The triples representation of concepts consists of concepts linked by relations in sentences represented by natural language. CSANN handles sentence data, which are difficult to handle since the data size is not unique, by decomposing the data into triples representations of concepts and integrating them into the semantic network format. It is verified by computer simulation that the proposed network can store sentences and recall sentences even if the input information is incomplete. Thus, the effectiveness of the proposed network in natural language processing is demonstrated.

AB - This paper proposes a new neural network (the concepts-of-sentences associative neural network, CSANN) which performs memory and recall of sentences represented by a semantic network, as an approach toward natural language processing. The semantic network is represented in terms of the triples representation of concepts. The triples representation of concepts consists of concepts linked by relations in sentences represented by natural language. CSANN handles sentence data, which are difficult to handle since the data size is not unique, by decomposing the data into triples representations of concepts and integrating them into the semantic network format. It is verified by computer simulation that the proposed network can store sentences and recall sentences even if the input information is incomplete. Thus, the effectiveness of the proposed network in natural language processing is demonstrated.

KW - Concept

KW - Distributed representation

KW - Multiple-winner self-organizing network

KW - Natural language

KW - Triples representation

UR - http://www.scopus.com/inward/record.url?scp=0141749316&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0141749316&partnerID=8YFLogxK

U2 - 10.1002/scj.10476

DO - 10.1002/scj.10476

M3 - Article

AN - SCOPUS:0141749316

VL - 34

SP - 43

EP - 54

JO - Systems and Computers in Japan

JF - Systems and Computers in Japan

SN - 0882-1666

IS - 11

ER -