Presentation 2003/7/21
Computational modeling of word meanings separation in vocabulary learning
Kousuke KUROSAKI, Takaomi KIMURA, Takashi OMORI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In general, words have various meanings, multiple in some case. So, to acquire the meaning of a word, we have to separate the meaning and learn them individually. In this paper, we used a simple computer game as a model of the real world, and performed experiments to make computer acquire the meanings of utterances from the environmental information and the illocutionary information by using "Structural Learning with Forgetting (Ishikawa, 1996)". If the words had polysemic meanings, we separate their meanings by using "Normal Mixtuer Model". As a result, the computer learned the meanings of the polysemic word according to the intention of a game player.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Language Acquisition / Structure Learning with Forgetting / Normal Mixture Model
Paper # NC2003-31
Date of Issue

Conference Information
Committee NC
Conference Date 2003/7/21(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Computational modeling of word meanings separation in vocabulary learning
Sub Title (in English)
Keyword(1) Language Acquisition
Keyword(2) Structure Learning with Forgetting
Keyword(3) Normal Mixture Model
1st Author's Name Kousuke KUROSAKI
1st Author's Affiliation Faculty of Engineering, Hokkaido University()
2nd Author's Name Takaomi KIMURA
2nd Author's Affiliation Sony Corporation
3rd Author's Name Takashi OMORI
3rd Author's Affiliation Faculty of Engineering, Hokkaido University
Date 2003/7/21
Paper # NC2003-31
Volume (vol) vol.103
Number (no) 227
Page pp.pp.-
#Pages 6
Date of Issue