Corpus of Multimodal Interaction for Collaborative Planning

Miltiadis Katsakioris; Atanas  Laskov; Ioannis Konstas; Helen Hastie

doi:10.18653/v1/W19-1601

Corpus of Multimodal Interaction for Collaborative Planning

Miltiadis Katsakioris, Atanas Laskov, Ioannis Konstas, Helen Hastie

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

43 Downloads (Pure)

Abstract

As autonomous systems become more commonplace, we need a way to easily and naturally communicate to them our goals and collaboratively come up with a plan on how to achieve these goals. To this end, we conducted a Wizard of Oz study to gather data and investigate the way operators would collaboratively make plans via a conversational {`}planning assistant{'} for remote autonomous systems. We present here a corpus of 22 dialogs from expert operators, which can be used to train such a system. Data analysis shows that multimodality is key to successful interaction, measured both quantitatively and qualitatively via user feedback.

Original language	English
Title of host publication	Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP)
Publisher	Association for Computational Linguistics
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781950737093
DOIs	https://doi.org/10.18653/v1/W19-1601
Publication status	Published - 6 Jun 2019
Event	RoboNLP at NAACL 2019 - Minneapolis, United States Duration: 3 Jun 2019 → …

Workshop

Workshop	RoboNLP at NAACL 2019
Country/Territory	United States
City	Minneapolis
Period	3/06/19 → …

Access to Document

10.18653/v1/W19-1601Licence: CC BY

Download pdfFinal published version, 2.51 MBLicence: CC BY

Cite this

@inproceedings{e718040bdfdf43a196b61c798fae04f2,

title = "Corpus of Multimodal Interaction for Collaborative Planning",

abstract = "As autonomous systems become more commonplace, we need a way to easily and naturally communicate to them our goals and collaboratively come up with a plan on how to achieve these goals. To this end, we conducted a Wizard of Oz study to gather data and investigate the way operators would collaboratively make plans via a conversational {`}planning assistant{'} for remote autonomous systems. We present here a corpus of 22 dialogs from expert operators, which can be used to train such a system. Data analysis shows that multimodality is key to successful interaction, measured both quantitatively and qualitatively via user feedback.",

author = "Miltiadis Katsakioris and Atanas Laskov and Ioannis Konstas and Helen Hastie",

year = "2019",

month = jun,

day = "6",

doi = "10.18653/v1/W19-1601",

language = "English",

pages = "1--6",

booktitle = "Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP)",

publisher = "Association for Computational Linguistics",

note = "RoboNLP at NAACL 2019 ; Conference date: 03-06-2019",

}

Katsakioris, M, Laskov, A, Konstas, I & Hastie, H 2019, Corpus of Multimodal Interaction for Collaborative Planning. in Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP). Association for Computational Linguistics, pp. 1-6, RoboNLP at NAACL 2019, Minneapolis, United States, 3/06/19. https://doi.org/10.18653/v1/W19-1601

Corpus of Multimodal Interaction for Collaborative Planning. / Katsakioris, Miltiadis; Laskov, Atanas ; Konstas, Ioannis et al.
Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP). Association for Computational Linguistics, 2019. p. 1-6.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Corpus of Multimodal Interaction for Collaborative Planning

AU - Katsakioris, Miltiadis

AU - Laskov, Atanas

AU - Konstas, Ioannis

AU - Hastie, Helen

PY - 2019/6/6

Y1 - 2019/6/6

N2 - As autonomous systems become more commonplace, we need a way to easily and naturally communicate to them our goals and collaboratively come up with a plan on how to achieve these goals. To this end, we conducted a Wizard of Oz study to gather data and investigate the way operators would collaboratively make plans via a conversational {`}planning assistant{'} for remote autonomous systems. We present here a corpus of 22 dialogs from expert operators, which can be used to train such a system. Data analysis shows that multimodality is key to successful interaction, measured both quantitatively and qualitatively via user feedback.

AB - As autonomous systems become more commonplace, we need a way to easily and naturally communicate to them our goals and collaboratively come up with a plan on how to achieve these goals. To this end, we conducted a Wizard of Oz study to gather data and investigate the way operators would collaboratively make plans via a conversational {`}planning assistant{'} for remote autonomous systems. We present here a corpus of 22 dialogs from expert operators, which can be used to train such a system. Data analysis shows that multimodality is key to successful interaction, measured both quantitatively and qualitatively via user feedback.

U2 - 10.18653/v1/W19-1601

DO - 10.18653/v1/W19-1601

M3 - Conference contribution

SP - 1

EP - 6

BT - Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP)

PB - Association for Computational Linguistics

T2 - RoboNLP at NAACL 2019

Y2 - 3 June 2019

ER -

Corpus of Multimodal Interaction for Collaborative Planning

Abstract

Workshop

Access to Document

Fingerprint

Cite this