A method for automatically generating proper responses to user's utterances in open-ended conversation by retrieving documents on the web

Masahiro Shibata, Tomomi Nishiguchi, Yoichi Tomiura

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We have been developing a new type of open-ended dialog system that generates a proper response to a user's utterance using the abundant documents on the World Wide Web as sources. Existing knowledge-based dialog systems give meaningful information to users, bitt they are unsuitable for open-ended input. The system Eliza can handle open-ended input, but it gives no meaningful information. Our system lies between the above two dialog systems; it converses 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 66% appropriate responses.

Original languageEnglish
Title of host publication2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008
Pages268-273
Number of pages6
DOIs
Publication statusPublished - Sep 23 2008
Event2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008 - Las Vegas, NV, United States
Duration: Jul 13 2008Jul 15 2008

Other

Other2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008
CountryUnited States
CityLas Vegas, NV
Period7/13/087/15/08

Fingerprint

Knowledge based systems
World Wide Web
Semantics

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Software

Cite this

Shibata, M., Nishiguchi, T., & Tomiura, Y. (2008). A method for automatically generating proper responses to user's utterances in open-ended conversation by retrieving documents on the web. In 2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008 (pp. 268-273). [4583041] https://doi.org/10.1109/IRI.2008.4583041

A method for automatically generating proper responses to user's utterances in open-ended conversation by retrieving documents on the web. / Shibata, Masahiro; Nishiguchi, Tomomi; Tomiura, Yoichi.

2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008. 2008. p. 268-273 4583041.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shibata, M, Nishiguchi, T & Tomiura, Y 2008, A method for automatically generating proper responses to user's utterances in open-ended conversation by retrieving documents on the web. in 2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008., 4583041, pp. 268-273, 2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008, Las Vegas, NV, United States, 7/13/08. https://doi.org/10.1109/IRI.2008.4583041
Shibata M, Nishiguchi T, Tomiura Y. A method for automatically generating proper responses to user's utterances in open-ended conversation by retrieving documents on the web. In 2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008. 2008. p. 268-273. 4583041 https://doi.org/10.1109/IRI.2008.4583041
Shibata, Masahiro ; Nishiguchi, Tomomi ; Tomiura, Yoichi. / A method for automatically generating proper responses to user's utterances in open-ended conversation by retrieving documents on the web. 2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008. 2008. pp. 268-273
@inproceedings{6e7c144b05cd421cb1d28114569f42bd,
title = "A method for automatically generating proper responses to user's utterances in open-ended conversation by retrieving documents on the web",
abstract = "We have been developing a new type of open-ended dialog system that generates a proper response to a user's utterance using the abundant documents on the World Wide Web as sources. Existing knowledge-based dialog systems give meaningful information to users, bitt they are unsuitable for open-ended input. The system Eliza can handle open-ended input, but it gives no meaningful information. Our system lies between the above two dialog systems; it converses 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 66{\%} appropriate responses.",
author = "Masahiro Shibata and Tomomi Nishiguchi and Yoichi Tomiura",
year = "2008",
month = "9",
day = "23",
doi = "10.1109/IRI.2008.4583041",
language = "English",
isbn = "9781424426607",
pages = "268--273",
booktitle = "2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008",

}

TY - GEN

T1 - A method for automatically generating proper responses to user's utterances in open-ended conversation by retrieving documents on the web

AU - Shibata, Masahiro

AU - Nishiguchi, Tomomi

AU - Tomiura, Yoichi

PY - 2008/9/23

Y1 - 2008/9/23

N2 - We have been developing a new type of open-ended dialog system that generates a proper response to a user's utterance using the abundant documents on the World Wide Web as sources. Existing knowledge-based dialog systems give meaningful information to users, bitt they are unsuitable for open-ended input. The system Eliza can handle open-ended input, but it gives no meaningful information. Our system lies between the above two dialog systems; it converses 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 66% appropriate responses.

AB - We have been developing a new type of open-ended dialog system that generates a proper response to a user's utterance using the abundant documents on the World Wide Web as sources. Existing knowledge-based dialog systems give meaningful information to users, bitt they are unsuitable for open-ended input. The system Eliza can handle open-ended input, but it gives no meaningful information. Our system lies between the above two dialog systems; it converses 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 66% appropriate responses.

UR - http://www.scopus.com/inward/record.url?scp=51949104737&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51949104737&partnerID=8YFLogxK

U2 - 10.1109/IRI.2008.4583041

DO - 10.1109/IRI.2008.4583041

M3 - Conference contribution

SN - 9781424426607

SP - 268

EP - 273

BT - 2008 IEEE International Conference on Information Reuse and Integration, IEEE IRI-2008

ER -