Intelligent agents: Conversations from human-agent imitation games

Research output: Chapter in Book/Report/Conference proceedingChapter

32 Downloads (Pure)

Abstract

What do humans say/ask beyond initial greetings? Are humans always the best at conversation? How easy is it to distinguish an intelligent human from an 'intelligent agent' just from their responses to unrestricted questions during a conversation? This paper presents an insight into the nature of human communications, including behaviours and interactions, from a type of interaction - stranger-to-stranger discourse realised from implementing Turing's question-answer imitation games at Bletchley Park UK in 2012 as part of the Turing centenary commemorations. The authors contend that the effects of lying, misunderstanding, humour and lack of shared knowledge during human-machine and human-human interactions can provide an impetus to building better conversational agents increasingly deployed as virtual customer service agents. Applying the findings could improve human-robot interaction, for example as conversational companions for the elderly or unwell. But do we always want these agents to talk like humans do? Suggestions to advance intelligent agent conversation are provided.
Original languageEnglish
Title of host publicationICAART 2015 - 7th International Conference on Agents and Artificial Intelligence, Proceedings
Editorsden Herik J. van, J. Filipe, S. Loiseau, B. Duval
PublisherSciTePress
Pages261-268
Volume2
ISBN (Print)978-989758074-1
Publication statusPublished - 2015
Event7th International Conference on Agents and Artificial Intelligence - Lisbon, Portugal
Duration: 10 Jan 201512 Jan 2015
Conference number: 7th
http://www.icaart.org/?y=2015

Conference

Conference7th International Conference on Agents and Artificial Intelligence
Abbreviated titleICAART 2015
CountryPortugal
CityLisbon
Period10/01/1512/01/15
Internet address

Fingerprint

Intelligent agents
Human robot interaction
Communication

Bibliographical note

This paper is not available on the repository. The paper was given at the 7th International Conference on Agents and Artificial Intelligence, ICAART 2015; Lisbon; Portugal; 10 January 2015 through 12 January 2015

Keywords

  • Artificial intelligence
  • Conversation
  • Imitation game
  • Intelligent agents
  • Linguistic devices

Cite this

Warwick, K., & Shah, H. (2015). Intelligent agents: Conversations from human-agent imitation games. In D. H. J. van, J. Filipe, S. Loiseau, & B. Duval (Eds.), ICAART 2015 - 7th International Conference on Agents and Artificial Intelligence, Proceedings (Vol. 2, pp. 261-268). SciTePress.

Intelligent agents: Conversations from human-agent imitation games. / Warwick, K.; Shah, H.

ICAART 2015 - 7th International Conference on Agents and Artificial Intelligence, Proceedings. ed. / den Herik J. van; J. Filipe; S. Loiseau; B. Duval. Vol. 2 SciTePress, 2015. p. 261-268.

Research output: Chapter in Book/Report/Conference proceedingChapter

Warwick, K & Shah, H 2015, Intelligent agents: Conversations from human-agent imitation games. in DHJ van, J Filipe, S Loiseau & B Duval (eds), ICAART 2015 - 7th International Conference on Agents and Artificial Intelligence, Proceedings. vol. 2, SciTePress, pp. 261-268, 7th International Conference on Agents and Artificial Intelligence , Lisbon, Portugal, 10/01/15.
Warwick K, Shah H. Intelligent agents: Conversations from human-agent imitation games. In van DHJ, Filipe J, Loiseau S, Duval B, editors, ICAART 2015 - 7th International Conference on Agents and Artificial Intelligence, Proceedings. Vol. 2. SciTePress. 2015. p. 261-268
Warwick, K. ; Shah, H. / Intelligent agents: Conversations from human-agent imitation games. ICAART 2015 - 7th International Conference on Agents and Artificial Intelligence, Proceedings. editor / den Herik J. van ; J. Filipe ; S. Loiseau ; B. Duval. Vol. 2 SciTePress, 2015. pp. 261-268
@inbook{f49de185d1b84ca5ba9493e4d7eea9d4,
title = "Intelligent agents: Conversations from human-agent imitation games",
abstract = "What do humans say/ask beyond initial greetings? Are humans always the best at conversation? How easy is it to distinguish an intelligent human from an 'intelligent agent' just from their responses to unrestricted questions during a conversation? This paper presents an insight into the nature of human communications, including behaviours and interactions, from a type of interaction - stranger-to-stranger discourse realised from implementing Turing's question-answer imitation games at Bletchley Park UK in 2012 as part of the Turing centenary commemorations. The authors contend that the effects of lying, misunderstanding, humour and lack of shared knowledge during human-machine and human-human interactions can provide an impetus to building better conversational agents increasingly deployed as virtual customer service agents. Applying the findings could improve human-robot interaction, for example as conversational companions for the elderly or unwell. But do we always want these agents to talk like humans do? Suggestions to advance intelligent agent conversation are provided.",
keywords = "Artificial intelligence, Conversation, Imitation game, Intelligent agents, Linguistic devices",
author = "K. Warwick and H. Shah",
note = "This paper is not available on the repository. The paper was given at the 7th International Conference on Agents and Artificial Intelligence, ICAART 2015; Lisbon; Portugal; 10 January 2015 through 12 January 2015",
year = "2015",
language = "English",
isbn = "978-989758074-1",
volume = "2",
pages = "261--268",
editor = "van, {den Herik J.} and J. Filipe and S. Loiseau and B. Duval",
booktitle = "ICAART 2015 - 7th International Conference on Agents and Artificial Intelligence, Proceedings",
publisher = "SciTePress",

}

TY - CHAP

T1 - Intelligent agents: Conversations from human-agent imitation games

AU - Warwick, K.

AU - Shah, H.

N1 - This paper is not available on the repository. The paper was given at the 7th International Conference on Agents and Artificial Intelligence, ICAART 2015; Lisbon; Portugal; 10 January 2015 through 12 January 2015

PY - 2015

Y1 - 2015

N2 - What do humans say/ask beyond initial greetings? Are humans always the best at conversation? How easy is it to distinguish an intelligent human from an 'intelligent agent' just from their responses to unrestricted questions during a conversation? This paper presents an insight into the nature of human communications, including behaviours and interactions, from a type of interaction - stranger-to-stranger discourse realised from implementing Turing's question-answer imitation games at Bletchley Park UK in 2012 as part of the Turing centenary commemorations. The authors contend that the effects of lying, misunderstanding, humour and lack of shared knowledge during human-machine and human-human interactions can provide an impetus to building better conversational agents increasingly deployed as virtual customer service agents. Applying the findings could improve human-robot interaction, for example as conversational companions for the elderly or unwell. But do we always want these agents to talk like humans do? Suggestions to advance intelligent agent conversation are provided.

AB - What do humans say/ask beyond initial greetings? Are humans always the best at conversation? How easy is it to distinguish an intelligent human from an 'intelligent agent' just from their responses to unrestricted questions during a conversation? This paper presents an insight into the nature of human communications, including behaviours and interactions, from a type of interaction - stranger-to-stranger discourse realised from implementing Turing's question-answer imitation games at Bletchley Park UK in 2012 as part of the Turing centenary commemorations. The authors contend that the effects of lying, misunderstanding, humour and lack of shared knowledge during human-machine and human-human interactions can provide an impetus to building better conversational agents increasingly deployed as virtual customer service agents. Applying the findings could improve human-robot interaction, for example as conversational companions for the elderly or unwell. But do we always want these agents to talk like humans do? Suggestions to advance intelligent agent conversation are provided.

KW - Artificial intelligence

KW - Conversation

KW - Imitation game

KW - Intelligent agents

KW - Linguistic devices

M3 - Chapter

SN - 978-989758074-1

VL - 2

SP - 261

EP - 268

BT - ICAART 2015 - 7th International Conference on Agents and Artificial Intelligence, Proceedings

A2 - van, den Herik J.

A2 - Filipe, J.

A2 - Loiseau, S.

A2 - Duval, B.

PB - SciTePress

ER -