Modeling Semantics and Pragmatics of Spatial Prepositions via Hierarchical Common-Sense Primitives

Georgiy Platonov, Yifei Yang, Haoyu Wu, Jonathan Waxman, Marcus Hill, Lenhart Schubert


Abstract
Understanding spatial expressions and using them appropriately is necessary for seamless and natural human-machine interaction. However, capturing the semantics and appropriate usage of spatial prepositions is notoriously difficult, because of their vagueness and polysemy. Although modern data-driven approaches are good at capturing statistical regularities in the usage, they usually require substantial sample sizes, often do not generalize well to unseen instances and, most importantly, their structure is essentially opaque to analysis, which makes diagnosing problems and understanding their reasoning process difficult. In this work, we discuss our attempt at modeling spatial senses of prepositions in English using a combination of rule-based and statistical learning approaches. Each preposition model is implemented as a tree where each node computes certain intuitive relations associated with the preposition, with the root computing the final value of the prepositional relation itself. The models operate on a set of artificial 3D “room world” environments, designed in Blender, taking the scene itself as an input. We also discuss our annotation framework used to collect human judgments employed in the model training. Both our factored models and black-box baseline models perform quite well, but the factored models will enable reasoned explanations of spatial relation judgements.
Anthology ID:
2021.splurobonlp-1.4
Volume:
Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics
Month:
August
Year:
2021
Address:
Online
Editors:
Malihe Alikhani, Valts Blukis, Parisa Kordjamshidi, Aishwarya Padmakumar, Hao Tan
Venue:
splurobonlp
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
32–41
Language:
URL:
https://aclanthology.org/2021.splurobonlp-1.4
DOI:
10.18653/v1/2021.splurobonlp-1.4
Bibkey:
Cite (ACL):
Georgiy Platonov, Yifei Yang, Haoyu Wu, Jonathan Waxman, Marcus Hill, and Lenhart Schubert. 2021. Modeling Semantics and Pragmatics of Spatial Prepositions via Hierarchical Common-Sense Primitives. In Proceedings of Second International Combined Workshop on Spatial Language Understanding and Grounded Communication for Robotics, pages 32–41, Online. Association for Computational Linguistics.
Cite (Informal):
Modeling Semantics and Pragmatics of Spatial Prepositions via Hierarchical Common-Sense Primitives (Platonov et al., splurobonlp 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.splurobonlp-1.4.pdf
Data
CLEVR