RE: Why - A prototype system for extracting answers of a "Why" type question from Web pages

Ushio Shibusawa, Takahiro Hayashi, Rikio Onai

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

There have been many studies on question-answering systems on the Web. Some of them try to find the answers to "Who","When" and "Where" type questions. However, there are few studies on practical systems which allow "Why" type questions. Because "Why" type questions need sentences for the answers and traditional and typical methods give the answers as a phrase or a word. Therfore we have proposed and implemented a prototype system "RE:Why" for extracting answers to a "Why" type question. RE:Why adopts new method which pays attention to the structual relations between sentences of a question and sentences of the answer on the Web. We have conducted experiments using twenty questions and have compared the performances between RE:Why and a traditional keyword search engine by measuring precisions and recalls.

Original languageEnglish
Pages (from-to)20-28
Number of pages9
JournalComputer Software
Volume24
Issue number3
Publication statusPublished - 2007
Externally publishedYes

Fingerprint

Search engines
Websites
Experiments

ASJC Scopus subject areas

  • Software

Cite this

RE : Why - A prototype system for extracting answers of a "Why" type question from Web pages. / Shibusawa, Ushio; Hayashi, Takahiro; Onai, Rikio.

In: Computer Software, Vol. 24, No. 3, 2007, p. 20-28.

Research output: Contribution to journalArticle

Shibusawa, U, Hayashi, T & Onai, R 2007, 'RE: Why - A prototype system for extracting answers of a "Why" type question from Web pages', Computer Software, vol. 24, no. 3, pp. 20-28.
Shibusawa, Ushio ; Hayashi, Takahiro ; Onai, Rikio. / RE : Why - A prototype system for extracting answers of a "Why" type question from Web pages. In: Computer Software. 2007 ; Vol. 24, No. 3. pp. 20-28.
@article{56631e2006ce4e7ca4c99666aca6268d,
title = "RE: Why - A prototype system for extracting answers of a {"}Why{"} type question from Web pages",
abstract = "There have been many studies on question-answering systems on the Web. Some of them try to find the answers to {"}Who{"},{"}When{"} and {"}Where{"} type questions. However, there are few studies on practical systems which allow {"}Why{"} type questions. Because {"}Why{"} type questions need sentences for the answers and traditional and typical methods give the answers as a phrase or a word. Therfore we have proposed and implemented a prototype system {"}RE:Why{"} for extracting answers to a {"}Why{"} type question. RE:Why adopts new method which pays attention to the structual relations between sentences of a question and sentences of the answer on the Web. We have conducted experiments using twenty questions and have compared the performances between RE:Why and a traditional keyword search engine by measuring precisions and recalls.",
author = "Ushio Shibusawa and Takahiro Hayashi and Rikio Onai",
year = "2007",
language = "English",
volume = "24",
pages = "20--28",
journal = "Computer Software",
issn = "0289-6540",
publisher = "Japan Society for Software Science and Technology",
number = "3",

}

TY - JOUR

T1 - RE

T2 - Why - A prototype system for extracting answers of a "Why" type question from Web pages

AU - Shibusawa, Ushio

AU - Hayashi, Takahiro

AU - Onai, Rikio

PY - 2007

Y1 - 2007

N2 - There have been many studies on question-answering systems on the Web. Some of them try to find the answers to "Who","When" and "Where" type questions. However, there are few studies on practical systems which allow "Why" type questions. Because "Why" type questions need sentences for the answers and traditional and typical methods give the answers as a phrase or a word. Therfore we have proposed and implemented a prototype system "RE:Why" for extracting answers to a "Why" type question. RE:Why adopts new method which pays attention to the structual relations between sentences of a question and sentences of the answer on the Web. We have conducted experiments using twenty questions and have compared the performances between RE:Why and a traditional keyword search engine by measuring precisions and recalls.

AB - There have been many studies on question-answering systems on the Web. Some of them try to find the answers to "Who","When" and "Where" type questions. However, there are few studies on practical systems which allow "Why" type questions. Because "Why" type questions need sentences for the answers and traditional and typical methods give the answers as a phrase or a word. Therfore we have proposed and implemented a prototype system "RE:Why" for extracting answers to a "Why" type question. RE:Why adopts new method which pays attention to the structual relations between sentences of a question and sentences of the answer on the Web. We have conducted experiments using twenty questions and have compared the performances between RE:Why and a traditional keyword search engine by measuring precisions and recalls.

UR - http://www.scopus.com/inward/record.url?scp=36949001581&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36949001581&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:36949001581

VL - 24

SP - 20

EP - 28

JO - Computer Software

JF - Computer Software

SN - 0289-6540

IS - 3

ER -