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

Takuya Ogura, Masafumi Hagiwara

Research output: Contribution to conferencePaperpeer-review

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
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

Conference

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

ASJC Scopus subject areas

  • Artificial Intelligence
  • Information Systems

Fingerprint

Dive into the research topics of 'A neural network type knowledge extraction method fromweb and its application to a question-answering system'. Together they form a unique fingerprint.

Cite this