A neural network type knowledge extraction method fromweb and its application to a question-answering system

Takuya Ogura, Masafumi Hagiwara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A neural network type knowledge extraction method from Web and its application to a question-answering system are proposed. In the proposed method, word groups of similar concepts locate in the same layer in the network. The idea is based on neuroscientific findings of Damasio's [9] and a cognitive scientific theory of McClelland's [10]. We carried out two kinds of experiments for the implemented question-answering system and obtained satisfactory results.

Original languageEnglish
Title of host publicationSCIS and ISIS 2010 - Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems
Pages171-176
Number of pages6
Publication statusPublished - 2010
EventJoint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2010 - Okayama, Japan
Duration: 2010 Dec 82010 Dec 12

Other

OtherJoint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2010
CountryJapan
CityOkayama
Period10/12/810/12/12

Fingerprint

Neural networks
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems

Cite this

Ogura, T., & Hagiwara, M. (2010). A neural network type knowledge extraction method fromweb and its application to a question-answering system. In SCIS and ISIS 2010 - Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems (pp. 171-176)

A neural network type knowledge extraction method fromweb and its application to a question-answering system. / Ogura, Takuya; Hagiwara, Masafumi.

SCIS and ISIS 2010 - Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems. 2010. p. 171-176.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ogura, T & Hagiwara, M 2010, A neural network type knowledge extraction method fromweb and its application to a question-answering system. in SCIS and ISIS 2010 - Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems. pp. 171-176, Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2010, Okayama, Japan, 10/12/8.
Ogura T, Hagiwara M. A neural network type knowledge extraction method fromweb and its application to a question-answering system. In SCIS and ISIS 2010 - Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems. 2010. p. 171-176
Ogura, Takuya ; Hagiwara, Masafumi. / A neural network type knowledge extraction method fromweb and its application to a question-answering system. SCIS and ISIS 2010 - Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems. 2010. pp. 171-176
@inproceedings{1b1d026a87c1408988087cd7b9cde55d,
title = "A neural network type knowledge extraction method fromweb and its application to a question-answering system",
abstract = "A neural network type knowledge extraction method from Web and its application to a question-answering system are proposed. In the proposed method, word groups of similar concepts locate in the same layer in the network. The idea is based on neuroscientific findings of Damasio's [9] and a cognitive scientific theory of McClelland's [10]. We carried out two kinds of experiments for the implemented question-answering system and obtained satisfactory results.",
author = "Takuya Ogura and Masafumi Hagiwara",
year = "2010",
language = "English",
pages = "171--176",
booktitle = "SCIS and ISIS 2010 - Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems",

}

TY - GEN

T1 - A neural network type knowledge extraction method fromweb and its application to a question-answering system

AU - Ogura, Takuya

AU - Hagiwara, Masafumi

PY - 2010

Y1 - 2010

N2 - A neural network type knowledge extraction method from Web and its application to a question-answering system are proposed. In the proposed method, word groups of similar concepts locate in the same layer in the network. The idea is based on neuroscientific findings of Damasio's [9] and a cognitive scientific theory of McClelland's [10]. We carried out two kinds of experiments for the implemented question-answering system and obtained satisfactory results.

AB - A neural network type knowledge extraction method from Web and its application to a question-answering system are proposed. In the proposed method, word groups of similar concepts locate in the same layer in the network. The idea is based on neuroscientific findings of Damasio's [9] and a cognitive scientific theory of McClelland's [10]. We carried out two kinds of experiments for the implemented question-answering system and obtained satisfactory results.

UR - http://www.scopus.com/inward/record.url?scp=84866692029&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866692029&partnerID=8YFLogxK

M3 - Conference contribution

SP - 171

EP - 176

BT - SCIS and ISIS 2010 - Joint 5th International Conference on Soft Computing and Intelligent Systems and 11th International Symposium on Advanced Intelligent Systems

ER -