Intelligent Web interface using flexible conversational agent with semantic bayesian networks

Kyoung Min Kim, Jin Hyuk Hong, Sung Bae Cho

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

3 Citations (Scopus)

Abstract

As on-line information services have become widespread in the Web nowadays, conversational agents appear as an effective and familiar user interface. Since conversational agents analyze the user's query based on a static process, it cannot manage complex expressions. In this paper, we propose semantic Bayesian networks that infer the user's intention based on Bayesian networks and their semantic information representing the relationship among nodes. Since conversation often contains ambiguous expressions, managing the context or the uncertainty should be necessary to support flexible conversational agents. The proposed method drives the mixed-initiative interaction (MII) that prompts for missing concepts and clarifies for spurious concepts to understand the user's intention correctly. Actually implementing a Web information guide with the proposed method, we have confirmed the usefulness of the proposed method.

Original languageEnglish
Title of host publicationProceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005
Pages313-318
Number of pages6
DOIs
Publication statusPublished - 2005 Dec 1
EventInternational Conference on Next Generation Web Services Practices, NWeSP 2005 - Seoul, Korea, Republic of
Duration: 2005 Aug 222005 Aug 26

Publication series

NameProceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005
Volume2005

Other

OtherInternational Conference on Next Generation Web Services Practices, NWeSP 2005
CountryKorea, Republic of
CitySeoul
Period05/8/2205/8/26

Fingerprint

Bayesian networks
Semantics
Information services
User interfaces

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Kim, K. M., Hong, J. H., & Cho, S. B. (2005). Intelligent Web interface using flexible conversational agent with semantic bayesian networks. In Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005 (pp. 313-318). [1592446] (Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005; Vol. 2005). https://doi.org/10.1109/NWESP.2005.51
Kim, Kyoung Min ; Hong, Jin Hyuk ; Cho, Sung Bae. / Intelligent Web interface using flexible conversational agent with semantic bayesian networks. Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005. 2005. pp. 313-318 (Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005).
@inproceedings{d857bbc907284ba5863c1ea1f1daffce,
title = "Intelligent Web interface using flexible conversational agent with semantic bayesian networks",
abstract = "As on-line information services have become widespread in the Web nowadays, conversational agents appear as an effective and familiar user interface. Since conversational agents analyze the user's query based on a static process, it cannot manage complex expressions. In this paper, we propose semantic Bayesian networks that infer the user's intention based on Bayesian networks and their semantic information representing the relationship among nodes. Since conversation often contains ambiguous expressions, managing the context or the uncertainty should be necessary to support flexible conversational agents. The proposed method drives the mixed-initiative interaction (MII) that prompts for missing concepts and clarifies for spurious concepts to understand the user's intention correctly. Actually implementing a Web information guide with the proposed method, we have confirmed the usefulness of the proposed method.",
author = "Kim, {Kyoung Min} and Hong, {Jin Hyuk} and Cho, {Sung Bae}",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/NWESP.2005.51",
language = "English",
isbn = "0769524524",
series = "Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005",
pages = "313--318",
booktitle = "Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005",

}

Kim, KM, Hong, JH & Cho, SB 2005, Intelligent Web interface using flexible conversational agent with semantic bayesian networks. in Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005., 1592446, Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005, vol. 2005, pp. 313-318, International Conference on Next Generation Web Services Practices, NWeSP 2005, Seoul, Korea, Republic of, 05/8/22. https://doi.org/10.1109/NWESP.2005.51

Intelligent Web interface using flexible conversational agent with semantic bayesian networks. / Kim, Kyoung Min; Hong, Jin Hyuk; Cho, Sung Bae.

Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005. 2005. p. 313-318 1592446 (Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005; Vol. 2005).

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

TY - GEN

T1 - Intelligent Web interface using flexible conversational agent with semantic bayesian networks

AU - Kim, Kyoung Min

AU - Hong, Jin Hyuk

AU - Cho, Sung Bae

PY - 2005/12/1

Y1 - 2005/12/1

N2 - As on-line information services have become widespread in the Web nowadays, conversational agents appear as an effective and familiar user interface. Since conversational agents analyze the user's query based on a static process, it cannot manage complex expressions. In this paper, we propose semantic Bayesian networks that infer the user's intention based on Bayesian networks and their semantic information representing the relationship among nodes. Since conversation often contains ambiguous expressions, managing the context or the uncertainty should be necessary to support flexible conversational agents. The proposed method drives the mixed-initiative interaction (MII) that prompts for missing concepts and clarifies for spurious concepts to understand the user's intention correctly. Actually implementing a Web information guide with the proposed method, we have confirmed the usefulness of the proposed method.

AB - As on-line information services have become widespread in the Web nowadays, conversational agents appear as an effective and familiar user interface. Since conversational agents analyze the user's query based on a static process, it cannot manage complex expressions. In this paper, we propose semantic Bayesian networks that infer the user's intention based on Bayesian networks and their semantic information representing the relationship among nodes. Since conversation often contains ambiguous expressions, managing the context or the uncertainty should be necessary to support flexible conversational agents. The proposed method drives the mixed-initiative interaction (MII) that prompts for missing concepts and clarifies for spurious concepts to understand the user's intention correctly. Actually implementing a Web information guide with the proposed method, we have confirmed the usefulness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=33847125795&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33847125795&partnerID=8YFLogxK

U2 - 10.1109/NWESP.2005.51

DO - 10.1109/NWESP.2005.51

M3 - Conference contribution

AN - SCOPUS:33847125795

SN - 0769524524

SN - 9780769524528

T3 - Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005

SP - 313

EP - 318

BT - Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005

ER -

Kim KM, Hong JH, Cho SB. Intelligent Web interface using flexible conversational agent with semantic bayesian networks. In Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005. 2005. p. 313-318. 1592446. (Proceedings - International Conference on Next Generation Web Services Practices, NWeSP 2005). https://doi.org/10.1109/NWESP.2005.51