Processing open text input in a scripted communication scenario

Extended abstract

J.T. Jeuring, Dascalu Mihai, Raja Lala, F.P.M. Heemskerk, Marcell Van Geest, Jordy Van Dortmont, Gabriel Gutu, Stefan Ruseti, Beatrice Alex, Richard Tobin

Research output: Chapter in Book/Report/Conference proceedingConference Abstract/Poster in proceedingAcademicpeer-review

18 Downloads (Pure)

Abstract

Serious games often employ pre-scripted dialogues and interactions with a player; in contrast to free user input that enables deeper immersion. In this paper we explore possibilities for interactive natural language dialogue in a serious game by combining Natural Language Processing (NLP) techniques with dialogue management. Our game learning environment has a communication scenario editor in which a domain expert develops a structured, scripted scenario as a sequence of potential interactions. A communication scenario is context-specific and often follows a protocol - for instance, delivering bad news to a patient. Currently, a player navigates through a simulation and converses with a virtual character by choosing a statement option from one of the prescripted player statements, at each step in the simulation. We develop a scenario-specific corpus method (SSCM) to process open responses (i.e. natural language inputs) in our learning environment. We conduct an experiment to collect data for comparing SSCM against multiple NLP methods, and another experiment to investigate if framing can improve processing open-text input using SSCM in a communication simulation.
Original languageEnglish
Title of host publicationSEMDIAL 2018 - AixDial
Subtitle of host publicationProceedings of the 22nd Workshop on the Semantics and Pragmatics of Dialogue
EditorsLaurent Prévot, Magalie Ochs, Benoît Favre
Place of PublicationAix-en-Provence
Pages211-214
Number of pages4
Publication statusPublished - Nov 2018
EventSEMDIAL 2018: The 22nd workshop on the Semantics and Pragmatics of Dialogue - Aix-en-Provence, France
Duration: 8 Nov 201810 Nov 2018
https://semdial.hypotheses.org/

Publication series

NameSEMDIAL 2018 proceedings

Conference

ConferenceSEMDIAL 2018
Abbreviated titleAixDIAL
CountryFrance
CityAix-en-Provence
Period8/11/1810/11/18
Internet address

Fingerprint

Communication
Processing
Experiments
Serious games

Keywords

  • NLP
  • dialogue management
  • RAGE
  • serious games

Cite this

Jeuring, J. T., Mihai, D., Lala, R., Heemskerk, F. P. M., Van Geest, M., Van Dortmont, J., ... Tobin, R. (2018). Processing open text input in a scripted communication scenario: Extended abstract. In L. Prévot, M. Ochs, & B. Favre (Eds.), SEMDIAL 2018 - AixDial: Proceedings of the 22nd Workshop on the Semantics and Pragmatics of Dialogue (pp. 211-214). (SEMDIAL 2018 proceedings). Aix-en-Provence.
Jeuring, J.T. ; Mihai, Dascalu ; Lala, Raja ; Heemskerk, F.P.M. ; Van Geest, Marcell ; Van Dortmont, Jordy ; Gutu, Gabriel ; Ruseti, Stefan ; Alex, Beatrice ; Tobin, Richard. / Processing open text input in a scripted communication scenario : Extended abstract. SEMDIAL 2018 - AixDial: Proceedings of the 22nd Workshop on the Semantics and Pragmatics of Dialogue. editor / Laurent Prévot ; Magalie Ochs ; Benoît Favre. Aix-en-Provence, 2018. pp. 211-214 (SEMDIAL 2018 proceedings).
@inbook{eec1b7bd46764fc2bc50d9c42dfae654,
title = "Processing open text input in a scripted communication scenario: Extended abstract",
abstract = "Serious games often employ pre-scripted dialogues and interactions with a player; in contrast to free user input that enables deeper immersion. In this paper we explore possibilities for interactive natural language dialogue in a serious game by combining Natural Language Processing (NLP) techniques with dialogue management. Our game learning environment has a communication scenario editor in which a domain expert develops a structured, scripted scenario as a sequence of potential interactions. A communication scenario is context-specific and often follows a protocol - for instance, delivering bad news to a patient. Currently, a player navigates through a simulation and converses with a virtual character by choosing a statement option from one of the prescripted player statements, at each step in the simulation. We develop a scenario-specific corpus method (SSCM) to process open responses (i.e. natural language inputs) in our learning environment. We conduct an experiment to collect data for comparing SSCM against multiple NLP methods, and another experiment to investigate if framing can improve processing open-text input using SSCM in a communication simulation.",
keywords = "NLP, dialogue management, RAGE, serious games",
author = "J.T. Jeuring and Dascalu Mihai and Raja Lala and F.P.M. Heemskerk and {Van Geest}, Marcell and {Van Dortmont}, Jordy and Gabriel Gutu and Stefan Ruseti and Beatrice Alex and Richard Tobin",
year = "2018",
month = "11",
language = "English",
series = "SEMDIAL 2018 proceedings",
pages = "211--214",
editor = "Laurent Pr{\'e}vot and Magalie Ochs and Beno{\^i}t Favre",
booktitle = "SEMDIAL 2018 - AixDial",

}

Jeuring, JT, Mihai, D, Lala, R, Heemskerk, FPM, Van Geest, M, Van Dortmont, J, Gutu, G, Ruseti, S, Alex, B & Tobin, R 2018, Processing open text input in a scripted communication scenario: Extended abstract. in L Prévot, M Ochs & B Favre (eds), SEMDIAL 2018 - AixDial: Proceedings of the 22nd Workshop on the Semantics and Pragmatics of Dialogue. SEMDIAL 2018 proceedings, Aix-en-Provence, pp. 211-214, SEMDIAL 2018, Aix-en-Provence, France, 8/11/18.

Processing open text input in a scripted communication scenario : Extended abstract. / Jeuring, J.T.; Mihai, Dascalu; Lala, Raja; Heemskerk, F.P.M.; Van Geest, Marcell; Van Dortmont, Jordy; Gutu, Gabriel; Ruseti, Stefan; Alex, Beatrice; Tobin, Richard.

SEMDIAL 2018 - AixDial: Proceedings of the 22nd Workshop on the Semantics and Pragmatics of Dialogue. ed. / Laurent Prévot; Magalie Ochs; Benoît Favre. Aix-en-Provence, 2018. p. 211-214 (SEMDIAL 2018 proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference Abstract/Poster in proceedingAcademicpeer-review

TY - CHAP

T1 - Processing open text input in a scripted communication scenario

T2 - Extended abstract

AU - Jeuring, J.T.

AU - Mihai, Dascalu

AU - Lala, Raja

AU - Heemskerk, F.P.M.

AU - Van Geest, Marcell

AU - Van Dortmont, Jordy

AU - Gutu, Gabriel

AU - Ruseti, Stefan

AU - Alex, Beatrice

AU - Tobin, Richard

PY - 2018/11

Y1 - 2018/11

N2 - Serious games often employ pre-scripted dialogues and interactions with a player; in contrast to free user input that enables deeper immersion. In this paper we explore possibilities for interactive natural language dialogue in a serious game by combining Natural Language Processing (NLP) techniques with dialogue management. Our game learning environment has a communication scenario editor in which a domain expert develops a structured, scripted scenario as a sequence of potential interactions. A communication scenario is context-specific and often follows a protocol - for instance, delivering bad news to a patient. Currently, a player navigates through a simulation and converses with a virtual character by choosing a statement option from one of the prescripted player statements, at each step in the simulation. We develop a scenario-specific corpus method (SSCM) to process open responses (i.e. natural language inputs) in our learning environment. We conduct an experiment to collect data for comparing SSCM against multiple NLP methods, and another experiment to investigate if framing can improve processing open-text input using SSCM in a communication simulation.

AB - Serious games often employ pre-scripted dialogues and interactions with a player; in contrast to free user input that enables deeper immersion. In this paper we explore possibilities for interactive natural language dialogue in a serious game by combining Natural Language Processing (NLP) techniques with dialogue management. Our game learning environment has a communication scenario editor in which a domain expert develops a structured, scripted scenario as a sequence of potential interactions. A communication scenario is context-specific and often follows a protocol - for instance, delivering bad news to a patient. Currently, a player navigates through a simulation and converses with a virtual character by choosing a statement option from one of the prescripted player statements, at each step in the simulation. We develop a scenario-specific corpus method (SSCM) to process open responses (i.e. natural language inputs) in our learning environment. We conduct an experiment to collect data for comparing SSCM against multiple NLP methods, and another experiment to investigate if framing can improve processing open-text input using SSCM in a communication simulation.

KW - NLP

KW - dialogue management

KW - RAGE

KW - serious games

M3 - Conference Abstract/Poster in proceeding

T3 - SEMDIAL 2018 proceedings

SP - 211

EP - 214

BT - SEMDIAL 2018 - AixDial

A2 - Prévot, Laurent

A2 - Ochs, Magalie

A2 - Favre, Benoît

CY - Aix-en-Provence

ER -

Jeuring JT, Mihai D, Lala R, Heemskerk FPM, Van Geest M, Van Dortmont J et al. Processing open text input in a scripted communication scenario: Extended abstract. In Prévot L, Ochs M, Favre B, editors, SEMDIAL 2018 - AixDial: Proceedings of the 22nd Workshop on the Semantics and Pragmatics of Dialogue. Aix-en-Provence. 2018. p. 211-214. (SEMDIAL 2018 proceedings).