Presentation 1995/12/14
How many words is a Picture Really Worth?
Laurel Fais, Kyung-ho Loken-Kim,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Subjects communicating in telephone and multimodal environments do not replace speech with visual images in the multimodal environment. Instead, they use more words in this environment. We discuss the trade-off between words and images, addressing this surprising result. Results from experiments in multimodal interpreted dialogues indicate that several factors are involved: a high number of redundant visual gestures; "meta-mode" conversation addressing the communication media themselves; and a slightly greater amount of information conveyed in the multimedia setting. Suggestions concerning integration of a multimedia system with automatic translation are made.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) multimedia / interpreted conversation / meta-conversation / automatic translation system
Paper # NLC95-52,SP95-87
Date of Issue

Conference Information
Committee NLC
Conference Date 1995/12/14(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 ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) How many words is a Picture Really Worth?
Sub Title (in English)
Keyword(1) multimedia
Keyword(2) interpreted conversation
Keyword(3) meta-conversation
Keyword(4) automatic translation system
1st Author's Name Laurel Fais
1st Author's Affiliation ATR Interpreting Telecommunications Research Laboratories()
2nd Author's Name Kyung-ho Loken-Kim
2nd Author's Affiliation ATR Interpreting Telecommunications Research Laboratories
Date 1995/12/14
Paper # NLC95-52,SP95-87
Volume (vol) vol.95
Number (no) 428
Page pp.pp.-
#Pages 7
Date of Issue