Extraction of questions behind messages

Naohiro Matsumura, Daisuke Kawahara, Masashi Okamoto, Sadao Kurohashi, Toyoaki Nishida

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

To overcome the limitation of conventional text-mining approaches in which frequent patterns of word occurrences are to be extracted to understand obvious user needs, this paper proposes an approach to extracting questions behind messages to understand potential user needs. We first extract characteristic case frames by comparing the case frames constructed from target messages with the ones from 25M sentences in the Web and 20M sentences in newspaper articles of 20 years. Then we extract questions behind messages by transforming the characteristic case frames into interrogative sentences based on new information and old information, i.e., replacing new information with WH-question words. The proposed approach is, in other words, a kind of classification of word occurrence pattern. Qualitative evaluations of our preliminary experiments suggest that extracted questions show problem consciousness and alternative solutions - all of which help to understand potential user needs.

Original languageEnglish
Pages (from-to)93-102
Number of pages10
JournalTransactions of the Japanese Society for Artificial Intelligence
Volume22
Issue number1
DOIs
Publication statusPublished - Jan 1 2007

Fingerprint

Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Matsumura, N., Kawahara, D., Okamoto, M., Kurohashi, S., & Nishida, T. (2007). Extraction of questions behind messages. Transactions of the Japanese Society for Artificial Intelligence, 22(1), 93-102. https://doi.org/10.1527/tjsai.22.93

Extraction of questions behind messages. / Matsumura, Naohiro; Kawahara, Daisuke; Okamoto, Masashi; Kurohashi, Sadao; Nishida, Toyoaki.

In: Transactions of the Japanese Society for Artificial Intelligence, Vol. 22, No. 1, 01.01.2007, p. 93-102.

Research output: Contribution to journalArticle

Matsumura, N, Kawahara, D, Okamoto, M, Kurohashi, S & Nishida, T 2007, 'Extraction of questions behind messages', Transactions of the Japanese Society for Artificial Intelligence, vol. 22, no. 1, pp. 93-102. https://doi.org/10.1527/tjsai.22.93
Matsumura, Naohiro ; Kawahara, Daisuke ; Okamoto, Masashi ; Kurohashi, Sadao ; Nishida, Toyoaki. / Extraction of questions behind messages. In: Transactions of the Japanese Society for Artificial Intelligence. 2007 ; Vol. 22, No. 1. pp. 93-102.
@article{d820c237b16245f1baa4cb0d31a165cd,
title = "Extraction of questions behind messages",
abstract = "To overcome the limitation of conventional text-mining approaches in which frequent patterns of word occurrences are to be extracted to understand obvious user needs, this paper proposes an approach to extracting questions behind messages to understand potential user needs. We first extract characteristic case frames by comparing the case frames constructed from target messages with the ones from 25M sentences in the Web and 20M sentences in newspaper articles of 20 years. Then we extract questions behind messages by transforming the characteristic case frames into interrogative sentences based on new information and old information, i.e., replacing new information with WH-question words. The proposed approach is, in other words, a kind of classification of word occurrence pattern. Qualitative evaluations of our preliminary experiments suggest that extracted questions show problem consciousness and alternative solutions - all of which help to understand potential user needs.",
author = "Naohiro Matsumura and Daisuke Kawahara and Masashi Okamoto and Sadao Kurohashi and Toyoaki Nishida",
year = "2007",
month = "1",
day = "1",
doi = "10.1527/tjsai.22.93",
language = "English",
volume = "22",
pages = "93--102",
journal = "Transactions of the Japanese Society for Artificial Intelligence",
issn = "1346-0714",
publisher = "Japanese Society for Artificial Intelligence",
number = "1",

}

TY - JOUR

T1 - Extraction of questions behind messages

AU - Matsumura, Naohiro

AU - Kawahara, Daisuke

AU - Okamoto, Masashi

AU - Kurohashi, Sadao

AU - Nishida, Toyoaki

PY - 2007/1/1

Y1 - 2007/1/1

N2 - To overcome the limitation of conventional text-mining approaches in which frequent patterns of word occurrences are to be extracted to understand obvious user needs, this paper proposes an approach to extracting questions behind messages to understand potential user needs. We first extract characteristic case frames by comparing the case frames constructed from target messages with the ones from 25M sentences in the Web and 20M sentences in newspaper articles of 20 years. Then we extract questions behind messages by transforming the characteristic case frames into interrogative sentences based on new information and old information, i.e., replacing new information with WH-question words. The proposed approach is, in other words, a kind of classification of word occurrence pattern. Qualitative evaluations of our preliminary experiments suggest that extracted questions show problem consciousness and alternative solutions - all of which help to understand potential user needs.

AB - To overcome the limitation of conventional text-mining approaches in which frequent patterns of word occurrences are to be extracted to understand obvious user needs, this paper proposes an approach to extracting questions behind messages to understand potential user needs. We first extract characteristic case frames by comparing the case frames constructed from target messages with the ones from 25M sentences in the Web and 20M sentences in newspaper articles of 20 years. Then we extract questions behind messages by transforming the characteristic case frames into interrogative sentences based on new information and old information, i.e., replacing new information with WH-question words. The proposed approach is, in other words, a kind of classification of word occurrence pattern. Qualitative evaluations of our preliminary experiments suggest that extracted questions show problem consciousness and alternative solutions - all of which help to understand potential user needs.

UR - http://www.scopus.com/inward/record.url?scp=33846641675&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846641675&partnerID=8YFLogxK

U2 - 10.1527/tjsai.22.93

DO - 10.1527/tjsai.22.93

M3 - Article

AN - SCOPUS:33846641675

VL - 22

SP - 93

EP - 102

JO - Transactions of the Japanese Society for Artificial Intelligence

JF - Transactions of the Japanese Society for Artificial Intelligence

SN - 1346-0714

IS - 1

ER -