Presentation 1999/3/5
Rertrieval of Simplified Causal Knowledge in Text and its Application
Hiroshi SATO, Kaname KASAHARA, Kazumitsu MATSUZAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A person has causal knowledge, and thinks before acting, "What will happen after this event?". To make a computer infer information as a person does, we are carrying out reserch on methods for automatically acquire, represent and apply causal knowledge. A conventional causal knowledge database must be manually constructed or limited in its domain because of its potential hugeness and deepness. However, Simplified Causal Knowledge, which we proposed in a previous paper, allows automatic retrieval from ordinary texts. In this paper, we evaluate this method with a large-scale text corpus.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) causal knowledge / common sense / knowledge acquisition / knowledge representation / dialogue / text corpus
Paper # TL98-23
Date of Issue

Conference Information
Committee TL
Conference Date 1999/3/5(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Thought and Language (TL)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Rertrieval of Simplified Causal Knowledge in Text and its Application
Sub Title (in English)
Keyword(1) causal knowledge
Keyword(2) common sense
Keyword(3) knowledge acquisition
Keyword(4) knowledge representation
Keyword(5) dialogue
Keyword(6) text corpus
1st Author's Name Hiroshi SATO
1st Author's Affiliation NTT Communication Science Laboratories()
2nd Author's Name Kaname KASAHARA
2nd Author's Affiliation NTT Communication Science Laboratories
3rd Author's Name Kazumitsu MATSUZAWA
3rd Author's Affiliation NTT Communication Science Laboratories
Date 1999/3/5
Paper # TL98-23
Volume (vol) vol.98
Number (no) 640
Page pp.pp.-
#Pages 8
Date of Issue