A Spontaneous Topic Change of Dialogue for Conversational Agent Based on Human Cognition and Memory

Sungsoo Lim, Keunhyun Oh, Sung Bae Cho

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

Abstract

Mixed-initiative interaction (MII) plays an important role for the flexible dialogues in conversational agent. Since conventional research on MII process dialogues based on the predefined methodologies, they only provide simple and static dialogues rather than complicated and dynamic dialogues through context-aware themselves. In this paper, we proposed a spontaneous conversational agent that provides MII and can change topics of dialogue dynamically based on human cognitive architecture and memory structure. Based on the global workspace theory, one of the simple cognitive architecture models, the proposed agent is aware of the context of dialogue in conscious level and chooses the topic in unconscious level which is the most relevant to the current context as the next topic of dialogues. We represent the unconscious part of memory using semantic network which is a popular representation for storing knowledge in the field of cognitive science, and retrieve the semantic network according to the spreading activation theory which is proven to be efficient for inferring in semantic networks. It is verified that the proposed method spontaneously changes the topics of dialogues through some dialogue examples on the domain of schedule management.

Original languageEnglish
Title of host publicationAgents and Artificial Intelligence - Second International Conference, ICAART 2010, Revised Selected Papers
EditorsJoaquim Filipe, Ana Fred, Bernadette Sharp
Pages91-100
Number of pages10
DOIs
Publication statusPublished - 2011 Dec 1
Event2nd International Conference on Agents and Artificial Intelligence, ICAART 2010 - Valencia, Spain
Duration: 2010 Jan 222010 Jan 24

Publication series

NameCommunications in Computer and Information Science
Volume129
ISSN (Print)1865-0929

Other

Other2nd International Conference on Agents and Artificial Intelligence, ICAART 2010
CountrySpain
CityValencia
Period10/1/2210/1/24

Fingerprint

Semantics
Data storage equipment
Chemical activation

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Mathematics(all)

Cite this

Lim, S., Oh, K., & Cho, S. B. (2011). A Spontaneous Topic Change of Dialogue for Conversational Agent Based on Human Cognition and Memory. In J. Filipe, A. Fred, & B. Sharp (Eds.), Agents and Artificial Intelligence - Second International Conference, ICAART 2010, Revised Selected Papers (pp. 91-100). (Communications in Computer and Information Science; Vol. 129). https://doi.org/10.1007/978-3-642-19890-8_7
Lim, Sungsoo ; Oh, Keunhyun ; Cho, Sung Bae. / A Spontaneous Topic Change of Dialogue for Conversational Agent Based on Human Cognition and Memory. Agents and Artificial Intelligence - Second International Conference, ICAART 2010, Revised Selected Papers. editor / Joaquim Filipe ; Ana Fred ; Bernadette Sharp. 2011. pp. 91-100 (Communications in Computer and Information Science).
@inproceedings{99f134db50ac458bbd63c2063fc18c30,
title = "A Spontaneous Topic Change of Dialogue for Conversational Agent Based on Human Cognition and Memory",
abstract = "Mixed-initiative interaction (MII) plays an important role for the flexible dialogues in conversational agent. Since conventional research on MII process dialogues based on the predefined methodologies, they only provide simple and static dialogues rather than complicated and dynamic dialogues through context-aware themselves. In this paper, we proposed a spontaneous conversational agent that provides MII and can change topics of dialogue dynamically based on human cognitive architecture and memory structure. Based on the global workspace theory, one of the simple cognitive architecture models, the proposed agent is aware of the context of dialogue in conscious level and chooses the topic in unconscious level which is the most relevant to the current context as the next topic of dialogues. We represent the unconscious part of memory using semantic network which is a popular representation for storing knowledge in the field of cognitive science, and retrieve the semantic network according to the spreading activation theory which is proven to be efficient for inferring in semantic networks. It is verified that the proposed method spontaneously changes the topics of dialogues through some dialogue examples on the domain of schedule management.",
author = "Sungsoo Lim and Keunhyun Oh and Cho, {Sung Bae}",
year = "2011",
month = "12",
day = "1",
doi = "10.1007/978-3-642-19890-8_7",
language = "English",
isbn = "9783642198892",
series = "Communications in Computer and Information Science",
pages = "91--100",
editor = "Joaquim Filipe and Ana Fred and Bernadette Sharp",
booktitle = "Agents and Artificial Intelligence - Second International Conference, ICAART 2010, Revised Selected Papers",

}

Lim, S, Oh, K & Cho, SB 2011, A Spontaneous Topic Change of Dialogue for Conversational Agent Based on Human Cognition and Memory. in J Filipe, A Fred & B Sharp (eds), Agents and Artificial Intelligence - Second International Conference, ICAART 2010, Revised Selected Papers. Communications in Computer and Information Science, vol. 129, pp. 91-100, 2nd International Conference on Agents and Artificial Intelligence, ICAART 2010, Valencia, Spain, 10/1/22. https://doi.org/10.1007/978-3-642-19890-8_7

A Spontaneous Topic Change of Dialogue for Conversational Agent Based on Human Cognition and Memory. / Lim, Sungsoo; Oh, Keunhyun; Cho, Sung Bae.

Agents and Artificial Intelligence - Second International Conference, ICAART 2010, Revised Selected Papers. ed. / Joaquim Filipe; Ana Fred; Bernadette Sharp. 2011. p. 91-100 (Communications in Computer and Information Science; Vol. 129).

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

TY - GEN

T1 - A Spontaneous Topic Change of Dialogue for Conversational Agent Based on Human Cognition and Memory

AU - Lim, Sungsoo

AU - Oh, Keunhyun

AU - Cho, Sung Bae

PY - 2011/12/1

Y1 - 2011/12/1

N2 - Mixed-initiative interaction (MII) plays an important role for the flexible dialogues in conversational agent. Since conventional research on MII process dialogues based on the predefined methodologies, they only provide simple and static dialogues rather than complicated and dynamic dialogues through context-aware themselves. In this paper, we proposed a spontaneous conversational agent that provides MII and can change topics of dialogue dynamically based on human cognitive architecture and memory structure. Based on the global workspace theory, one of the simple cognitive architecture models, the proposed agent is aware of the context of dialogue in conscious level and chooses the topic in unconscious level which is the most relevant to the current context as the next topic of dialogues. We represent the unconscious part of memory using semantic network which is a popular representation for storing knowledge in the field of cognitive science, and retrieve the semantic network according to the spreading activation theory which is proven to be efficient for inferring in semantic networks. It is verified that the proposed method spontaneously changes the topics of dialogues through some dialogue examples on the domain of schedule management.

AB - Mixed-initiative interaction (MII) plays an important role for the flexible dialogues in conversational agent. Since conventional research on MII process dialogues based on the predefined methodologies, they only provide simple and static dialogues rather than complicated and dynamic dialogues through context-aware themselves. In this paper, we proposed a spontaneous conversational agent that provides MII and can change topics of dialogue dynamically based on human cognitive architecture and memory structure. Based on the global workspace theory, one of the simple cognitive architecture models, the proposed agent is aware of the context of dialogue in conscious level and chooses the topic in unconscious level which is the most relevant to the current context as the next topic of dialogues. We represent the unconscious part of memory using semantic network which is a popular representation for storing knowledge in the field of cognitive science, and retrieve the semantic network according to the spreading activation theory which is proven to be efficient for inferring in semantic networks. It is verified that the proposed method spontaneously changes the topics of dialogues through some dialogue examples on the domain of schedule management.

UR - http://www.scopus.com/inward/record.url?scp=84879473468&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879473468&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-19890-8_7

DO - 10.1007/978-3-642-19890-8_7

M3 - Conference contribution

AN - SCOPUS:84879473468

SN - 9783642198892

T3 - Communications in Computer and Information Science

SP - 91

EP - 100

BT - Agents and Artificial Intelligence - Second International Conference, ICAART 2010, Revised Selected Papers

A2 - Filipe, Joaquim

A2 - Fred, Ana

A2 - Sharp, Bernadette

ER -

Lim S, Oh K, Cho SB. A Spontaneous Topic Change of Dialogue for Conversational Agent Based on Human Cognition and Memory. In Filipe J, Fred A, Sharp B, editors, Agents and Artificial Intelligence - Second International Conference, ICAART 2010, Revised Selected Papers. 2011. p. 91-100. (Communications in Computer and Information Science). https://doi.org/10.1007/978-3-642-19890-8_7