Presentation | 1998/10/16 An emotion calculate method by word-feeling from natural language dialog Kazuya Mera, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Formerly we proposed a system to realize free-development type dialog. The system specially paid attentions to emotion generation by "substituting word-feeling value of subject, object and predicate to a common expression". In this paper, we try to improve the emotion generation method. Only binary output of emotion is allowed. New method can adopt 17 types of predicates ad well as negative sentences and noun phrase. Our hand simulation by actual 190 dialog sentences shows that the correct rate of emotion generation increases to 71.1%. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | dialog / emotion / emotion generate expression / word-feeling value / case frame |
Paper # | NLC98-26 |
Date of Issue |
Conference Information | |
Committee | NLC |
---|---|
Conference Date | 1998/10/16(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 | Natural Language Understanding and Models of Communication (NLC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | An emotion calculate method by word-feeling from natural language dialog |
Sub Title (in English) | |
Keyword(1) | dialog |
Keyword(2) | emotion |
Keyword(3) | emotion generate expression |
Keyword(4) | word-feeling value |
Keyword(5) | case frame |
1st Author's Name | Kazuya Mera |
1st Author's Affiliation | Faculty of Information Science Hiroshima City University() |
Date | 1998/10/16 |
Paper # | NLC98-26 |
Volume (vol) | vol.98 |
Number (no) | 338 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |