A semantic Bayesian network approach to retrieving information with intelligent conversational agents

Kyoung Min Kim, Jin Hyuk Hong, Sung-Bae Cho

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

As access to information becomes more intensive in society, a great deal of that information is becoming available through diverse channels. Accordingly, users require effective methods for accessing this information. Conversational agents can act as effective and familiar user interfaces. Although conversational agents can analyze the queries of users based on a static process, they cannot manage expressions that are more complex. In this paper, we propose a system that uses semantic Bayesian networks to infer the intentions of the user based on Bayesian networks and their semantic information. Since conversation often contains ambiguous expressions, the managing of context and uncertainty is necessary to support flexible conversational agents. The proposed method uses mixed-initiative interaction (MII) to obtain missing information and clarify spurious concepts in order to understand the intention of users correctly. We applied this to an information retrieval service for websites to verify the usefulness of the proposed method.

Original languageEnglish
Pages (from-to)225-236
Number of pages12
JournalInformation Processing and Management
Volume43
Issue number1
DOIs
Publication statusPublished - 2007 Jan 1

Fingerprint

Intelligent agents
Bayesian networks
Semantics
semantics
Information retrieval
User interfaces
Websites
user interface
information retrieval
website
conversation
uncertainty
interaction
Uncertainty

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Media Technology
  • Computer Science Applications
  • Management Science and Operations Research
  • Library and Information Sciences

Cite this

@article{f756c04b936246d3a60a2730e58ba7dc,
title = "A semantic Bayesian network approach to retrieving information with intelligent conversational agents",
abstract = "As access to information becomes more intensive in society, a great deal of that information is becoming available through diverse channels. Accordingly, users require effective methods for accessing this information. Conversational agents can act as effective and familiar user interfaces. Although conversational agents can analyze the queries of users based on a static process, they cannot manage expressions that are more complex. In this paper, we propose a system that uses semantic Bayesian networks to infer the intentions of the user based on Bayesian networks and their semantic information. Since conversation often contains ambiguous expressions, the managing of context and uncertainty is necessary to support flexible conversational agents. The proposed method uses mixed-initiative interaction (MII) to obtain missing information and clarify spurious concepts in order to understand the intention of users correctly. We applied this to an information retrieval service for websites to verify the usefulness of the proposed method.",
author = "Kim, {Kyoung Min} and Hong, {Jin Hyuk} and Sung-Bae Cho",
year = "2007",
month = "1",
day = "1",
doi = "10.1016/j.ipm.2006.04.001",
language = "English",
volume = "43",
pages = "225--236",
journal = "Information Processing and Management",
issn = "0306-4573",
publisher = "Elsevier Limited",
number = "1",

}

A semantic Bayesian network approach to retrieving information with intelligent conversational agents. / Kim, Kyoung Min; Hong, Jin Hyuk; Cho, Sung-Bae.

In: Information Processing and Management, Vol. 43, No. 1, 01.01.2007, p. 225-236.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A semantic Bayesian network approach to retrieving information with intelligent conversational agents

AU - Kim, Kyoung Min

AU - Hong, Jin Hyuk

AU - Cho, Sung-Bae

PY - 2007/1/1

Y1 - 2007/1/1

N2 - As access to information becomes more intensive in society, a great deal of that information is becoming available through diverse channels. Accordingly, users require effective methods for accessing this information. Conversational agents can act as effective and familiar user interfaces. Although conversational agents can analyze the queries of users based on a static process, they cannot manage expressions that are more complex. In this paper, we propose a system that uses semantic Bayesian networks to infer the intentions of the user based on Bayesian networks and their semantic information. Since conversation often contains ambiguous expressions, the managing of context and uncertainty is necessary to support flexible conversational agents. The proposed method uses mixed-initiative interaction (MII) to obtain missing information and clarify spurious concepts in order to understand the intention of users correctly. We applied this to an information retrieval service for websites to verify the usefulness of the proposed method.

AB - As access to information becomes more intensive in society, a great deal of that information is becoming available through diverse channels. Accordingly, users require effective methods for accessing this information. Conversational agents can act as effective and familiar user interfaces. Although conversational agents can analyze the queries of users based on a static process, they cannot manage expressions that are more complex. In this paper, we propose a system that uses semantic Bayesian networks to infer the intentions of the user based on Bayesian networks and their semantic information. Since conversation often contains ambiguous expressions, the managing of context and uncertainty is necessary to support flexible conversational agents. The proposed method uses mixed-initiative interaction (MII) to obtain missing information and clarify spurious concepts in order to understand the intention of users correctly. We applied this to an information retrieval service for websites to verify the usefulness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=33748289948&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748289948&partnerID=8YFLogxK

U2 - 10.1016/j.ipm.2006.04.001

DO - 10.1016/j.ipm.2006.04.001

M3 - Article

VL - 43

SP - 225

EP - 236

JO - Information Processing and Management

JF - Information Processing and Management

SN - 0306-4573

IS - 1

ER -