Domain-adaptive conversational agent with two-stage dialogue management

Jin Hyuk Hong, Sung Bae Cho

Research output: Contribution to journalConference article

4 Citations (Scopus)

Abstract

The conversational agent understands and provides users with proper information based on natural language. Conventional agents based on pattern matching have much restriction to manage various types of real dialogues and to improve the answering performance. For the effective construction of conversational agents, we propose a domain-adaptive conversational agent that infers the user's intention with two-stage inference and incrementally improves the answering performance through a learning dialogue. We can confirm the usefulness of the proposed method with examples and usability tests.

Original languageEnglish
Pages (from-to)1147-1153
Number of pages7
JournalLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume3339
Publication statusPublished - 2004 Dec 1
Event17th Australian Joint Conference on Artificial Intelligence, AI 2004: Advances in Artificial Intelligence - Cairns, Australia
Duration: 2004 Dec 42004 Dec 6

Fingerprint

Dialogue Management
Pattern matching
Usability Test
Pattern Matching
Natural Language
Restriction
Dialogue

All Science Journal Classification (ASJC) codes

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

@article{6ba4ebfd3cb64934a59746d65313af12,
title = "Domain-adaptive conversational agent with two-stage dialogue management",
abstract = "The conversational agent understands and provides users with proper information based on natural language. Conventional agents based on pattern matching have much restriction to manage various types of real dialogues and to improve the answering performance. For the effective construction of conversational agents, we propose a domain-adaptive conversational agent that infers the user's intention with two-stage inference and incrementally improves the answering performance through a learning dialogue. We can confirm the usefulness of the proposed method with examples and usability tests.",
author = "Hong, {Jin Hyuk} and Cho, {Sung Bae}",
year = "2004",
month = "12",
day = "1",
language = "English",
volume = "3339",
pages = "1147--1153",
journal = "Lecture Notes in Computer Science",
issn = "0302-9743",
publisher = "Springer Verlag",

}

Domain-adaptive conversational agent with two-stage dialogue management. / Hong, Jin Hyuk; Cho, Sung Bae.

In: Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science), Vol. 3339, 01.12.2004, p. 1147-1153.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Domain-adaptive conversational agent with two-stage dialogue management

AU - Hong, Jin Hyuk

AU - Cho, Sung Bae

PY - 2004/12/1

Y1 - 2004/12/1

N2 - The conversational agent understands and provides users with proper information based on natural language. Conventional agents based on pattern matching have much restriction to manage various types of real dialogues and to improve the answering performance. For the effective construction of conversational agents, we propose a domain-adaptive conversational agent that infers the user's intention with two-stage inference and incrementally improves the answering performance through a learning dialogue. We can confirm the usefulness of the proposed method with examples and usability tests.

AB - The conversational agent understands and provides users with proper information based on natural language. Conventional agents based on pattern matching have much restriction to manage various types of real dialogues and to improve the answering performance. For the effective construction of conversational agents, we propose a domain-adaptive conversational agent that infers the user's intention with two-stage inference and incrementally improves the answering performance through a learning dialogue. We can confirm the usefulness of the proposed method with examples and usability tests.

UR - http://www.scopus.com/inward/record.url?scp=22944457535&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=22944457535&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:22944457535

VL - 3339

SP - 1147

EP - 1153

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

SN - 0302-9743

ER -