A Two-Level Interpretation of Modality in Human-Robot Dialogue

Lucia Donatelli, Kenneth Lai, James Pustejovsky


Abstract
We analyze the use and interpretation of modal expressions in a corpus of situated human-robot dialogue and ask how to effectively represent these expressions for automatic learning. We present a two-level annotation scheme for modality that captures both content and intent, integrating a logic-based, semantic representation and a task-oriented, pragmatic representation that maps to our robot’s capabilities. Data from our annotation task reveals that the interpretation of modal expressions in human-robot dialogue is quite diverse, yet highly constrained by the physical environment and asymmetrical speaker/addressee relationship. We sketch a formal model of human-robot common ground in which modality can be grounded and dynamically interpreted.
Anthology ID:
2020.coling-main.373
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Editors:
Donia Scott, Nuria Bel, Chengqing Zong
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
4222–4238
Language:
URL:
https://aclanthology.org/2020.coling-main.373
DOI:
10.18653/v1/2020.coling-main.373
Bibkey:
Cite (ACL):
Lucia Donatelli, Kenneth Lai, and James Pustejovsky. 2020. A Two-Level Interpretation of Modality in Human-Robot Dialogue. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4222–4238, Barcelona, Spain (Online). International Committee on Computational Linguistics.
Cite (Informal):
A Two-Level Interpretation of Modality in Human-Robot Dialogue (Donatelli et al., COLING 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.373.pdf
Data
MPQA Opinion Corpus