Presentation 2002/1/2
The New Lexicalselection System Baced on Multivariate Numerical Data
Nami HORIGUCHI, Koichiro HAJIRI, Eitaro AIYOSHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a new lexical selection algorithm for the utterance production from mental lexicon. Until now, lexical selection concerned with the state of mind was described as reference process based on information which was decided come up to conception. The algorithm in this study is based on multivariate numerical data processing and paid attention to context-dependency and waver-traits characteristics of human emotions. In the computation process on the point of synonyms or emotional contexts, and the performance of this system will have autonomous sense achieving much organic performance. Moreover, we have implemented this algorithm and made an evaluation. As the conclusion, we got that our new algorithm has much more organic and autonomous lexical selection behavior more than former models.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) lexicalselection system / self-orzanization / chaos / emotion
Paper # 2001-AI-56
Date of Issue

Conference Information
Committee AI
Conference Date 2002/1/2(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 Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The New Lexicalselection System Baced on Multivariate Numerical Data
Sub Title (in English)
Keyword(1) lexicalselection system
Keyword(2) self-orzanization
Keyword(3) chaos
Keyword(4) emotion
1st Author's Name Nami HORIGUCHI
1st Author's Affiliation Faculty of Science and Technology, Keio University()
2nd Author's Name Koichiro HAJIRI
2nd Author's Affiliation IBM Tokyo Research Laboratory
3rd Author's Name Eitaro AIYOSHI
3rd Author's Affiliation Faculty of Science and Technology, Keio University
Date 2002/1/2
Paper # 2001-AI-56
Volume (vol) vol.101
Number (no) 535
Page pp.pp.-
#Pages 8
Date of Issue