Presentation 2004/10/29
Relative Ranking of Degree Modifiers and Its Application to Impression-Based Content-Retrieval by Natural Language Input
Tadahiko KUMAMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When we use impression-based multimedia retrieval systems where impressions such as "happy" and "bright" are input, we want to use degree modifiers such "adequately" and "comparatively" in order to more accurately express the impression we want to input. In conventional impression-based retrieval systems, however, at most two or three typical degree modifiers can be accepted. In this article, therefore, we extract 119 degree modifiers from the thesaurus, and numerically express the semantic role of each degree modifier. The semantic role of a degree modifier is defined as strengthening or weakening the meanings of the impression word which has been modified by the degree modifier, and all the degree modifiers are arranged according to their strength.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Adverbs representing a degree / multimedia retrieval / kansei retrieval / natural language interface
Paper # NLC2004-23
Date of Issue

Conference Information
Committee NLC
Conference Date 2004/10/29(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) Relative Ranking of Degree Modifiers and Its Application to Impression-Based Content-Retrieval by Natural Language Input
Sub Title (in English)
Keyword(1) Adverbs representing a degree
Keyword(2) multimedia retrieval
Keyword(3) kansei retrieval
Keyword(4) natural language interface
1st Author's Name Tadahiko KUMAMOTO
1st Author's Affiliation Keihanna Human Info Communication Research Center, National Institute of Information and Communications Technology()
Date 2004/10/29
Paper # NLC2004-23
Volume (vol) vol.104
Number (no) 417
Page pp.pp.-
#Pages 6
Date of Issue