Presentation 2013-10-19
Knowledge Acquisition by Hierarchical Structured Semantic Space Model.
Akinori TAKADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this article I propose "Hierarchical Structured Semantic Space Model" as a method to construct natural language based question-answering system. In rule-based natural language processing, input sentences are needed to be translated into certain types of meta-form, and there are some problems as below: (1) how we translate sentences like "I think that ..." or "He believes that ...", (2) how we manage contradictions in sentences input by two persons, (3) how we get logically consistent knowledge from various sentences with miscellaneous types. In this proposed method, individually separated semantic spaces having hierarchical structure in virtually placed main system are constructed, and meta-form data in lower semantic space such as "fact" or "logic" are appropriately transformed and brought up into upper semantic space. Further problems are discussed along with examples of implemented system.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) natural language processing / question-answering system / semantic space / knowledge acquisition
Paper # TL2013-46
Date of Issue

Conference Information
Committee TL
Conference Date 2013/10/12(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Vice Chair

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) Knowledge Acquisition by Hierarchical Structured Semantic Space Model.
Sub Title (in English)
Keyword(1) natural language processing
Keyword(2) question-answering system
Keyword(3) semantic space
Keyword(4) knowledge acquisition
1st Author's Name Akinori TAKADA
1st Author's Affiliation Faculty of Letters, Department of Communication Studies, Ferris University()
Date 2013-10-19
Paper # TL2013-46
Volume (vol) vol.113
Number (no) 253
Page pp.pp.-
#Pages 6
Date of Issue