Dialog system for open-ended conversation using web documents

Masahiro Shibata, Tomomi Nishiguchi, Yoichi Tomiura

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

We have developed a new type of open-ended dialog system that generates proper responses to users' utterances using the abundant documents available on the World Wide Web as sources. Existing knowledge-based dialog systems rovide meaningful information to users, but they are unsuitable for open-ended input. The system Eliza, while it can handle open-ended input, gives no meaningful information. Our system lies between the above two dialog systems; it can converse on various topics and gives meaningful information related to the user's utterances. The system selects an appropriate sentence as a response from documents gathered through the Web on the basis of surface cohesion and shallow semantic coherence. We developed a trial system to converse about movies and experimentally found that the proposed method generated appropriate responses at a rate of 66%.

Original languageEnglish
Pages (from-to)277-284
Number of pages8
JournalInformatica (Ljubljana)
Volume33
Issue number3
Publication statusPublished - Oct 26 2009

Fingerprint

Dialogue Systems
Knowledge based systems
World Wide Web
Semantics
Converse
Cohesion
Knowledge-based Systems
Open Systems

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Dialog system for open-ended conversation using web documents. / Shibata, Masahiro; Nishiguchi, Tomomi; Tomiura, Yoichi.

In: Informatica (Ljubljana), Vol. 33, No. 3, 26.10.2009, p. 277-284.

Research output: Contribution to journalArticle

Shibata, M, Nishiguchi, T & Tomiura, Y 2009, 'Dialog system for open-ended conversation using web documents', Informatica (Ljubljana), vol. 33, no. 3, pp. 277-284.
Shibata, Masahiro ; Nishiguchi, Tomomi ; Tomiura, Yoichi. / Dialog system for open-ended conversation using web documents. In: Informatica (Ljubljana). 2009 ; Vol. 33, No. 3. pp. 277-284.
@article{644eb83714784e3e91bef8bfc756d929,
title = "Dialog system for open-ended conversation using web documents",
abstract = "We have developed a new type of open-ended dialog system that generates proper responses to users' utterances using the abundant documents available on the World Wide Web as sources. Existing knowledge-based dialog systems rovide meaningful information to users, but they are unsuitable for open-ended input. The system Eliza, while it can handle open-ended input, gives no meaningful information. Our system lies between the above two dialog systems; it can converse on various topics and gives meaningful information related to the user's utterances. The system selects an appropriate sentence as a response from documents gathered through the Web on the basis of surface cohesion and shallow semantic coherence. We developed a trial system to converse about movies and experimentally found that the proposed method generated appropriate responses at a rate of 66{\%}.",
author = "Masahiro Shibata and Tomomi Nishiguchi and Yoichi Tomiura",
year = "2009",
month = "10",
day = "26",
language = "English",
volume = "33",
pages = "277--284",
journal = "Informatica (Slovenia)",
issn = "0350-5596",
publisher = "Slovene Society Informatika",
number = "3",

}

TY - JOUR

T1 - Dialog system for open-ended conversation using web documents

AU - Shibata, Masahiro

AU - Nishiguchi, Tomomi

AU - Tomiura, Yoichi

PY - 2009/10/26

Y1 - 2009/10/26

N2 - We have developed a new type of open-ended dialog system that generates proper responses to users' utterances using the abundant documents available on the World Wide Web as sources. Existing knowledge-based dialog systems rovide meaningful information to users, but they are unsuitable for open-ended input. The system Eliza, while it can handle open-ended input, gives no meaningful information. Our system lies between the above two dialog systems; it can converse on various topics and gives meaningful information related to the user's utterances. The system selects an appropriate sentence as a response from documents gathered through the Web on the basis of surface cohesion and shallow semantic coherence. We developed a trial system to converse about movies and experimentally found that the proposed method generated appropriate responses at a rate of 66%.

AB - We have developed a new type of open-ended dialog system that generates proper responses to users' utterances using the abundant documents available on the World Wide Web as sources. Existing knowledge-based dialog systems rovide meaningful information to users, but they are unsuitable for open-ended input. The system Eliza, while it can handle open-ended input, gives no meaningful information. Our system lies between the above two dialog systems; it can converse on various topics and gives meaningful information related to the user's utterances. The system selects an appropriate sentence as a response from documents gathered through the Web on the basis of surface cohesion and shallow semantic coherence. We developed a trial system to converse about movies and experimentally found that the proposed method generated appropriate responses at a rate of 66%.

UR - http://www.scopus.com/inward/record.url?scp=70350157929&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350157929&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:70350157929

VL - 33

SP - 277

EP - 284

JO - Informatica (Slovenia)

JF - Informatica (Slovenia)

SN - 0350-5596

IS - 3

ER -