Presentation 2005-06-17
Impression Mining from Text and Its Application to Web Retrieval
Tadahiko KUMAMOTO, Katsumi TANAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have been developing a novel Web-based question answering system that collects people's opinions about a user's question or concern on the Web, and shows a general view and summarization of the opinions. This system will be able to answer users' questions requesting opinions, for example, "How do people think about mothers always getting angry?" In this paper, we propose a system that collects the Web pages which are related with a user's question, extracts impressions from each of the Web pages, and plots the results on an impression plane. Users can take a general view of people's opinions about their concern through two impression planes; One is a plane spanned by impression scales "Anticipation-Surprise" and "Acceptance-Disgust", and the other is a plane spanned by impression scales "Joy-Sadness" and "Fear-Anger". Note that, in this system, the impressions of a text part are represented as scale values between 0 and 1 in the four impression scales mentioned above.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Question answering / impression mining / query expansion / paraphrasing / impression-based view
Paper # DE2005-28,PRMU2005-49
Date of Issue

Conference Information
Committee DE
Conference Date 2005/6/10(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 Data Engineering (DE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Impression Mining from Text and Its Application to Web Retrieval
Sub Title (in English)
Keyword(1) Question answering
Keyword(2) impression mining
Keyword(3) query expansion
Keyword(4) paraphrasing
Keyword(5) impression-based view
1st Author's Name Tadahiko KUMAMOTO
1st Author's Affiliation Keihanna Human Info-Communication Research Center, National Institute of Information and Communications Technology()
2nd Author's Name Katsumi TANAKA
2nd Author's Affiliation Keihanna Human Info-Communication Research Center, National Institute of Information and Communications Technology:Graduate School of Informatics, Kyoto University
Date 2005-06-17
Paper # DE2005-28,PRMU2005-49
Volume (vol) vol.105
Number (no) 117
Page pp.pp.-
#Pages 6
Date of Issue