What a neural language model tells us about spatial relations

Mehdi Ghanimifard, Simon Dobnik


Abstract
Understanding and generating spatial descriptions requires knowledge about what objects are related, their functional interactions, and where the objects are geometrically located. Different spatial relations have different functional and geometric bias. The wide usage of neural language models in different areas including generation of image description motivates the study of what kind of knowledge is encoded in neural language models about individual spatial relations. With the premise that the functional bias of relations is expressed in their word distributions, we construct multi-word distributional vector representations and show that these representations perform well on intrinsic semantic reasoning tasks, thus confirming our premise. A comparison of our vector representations to human semantic judgments indicates that different bias (functional or geometric) is captured in different data collection tasks which suggests that the contribution of the two meaning modalities is dynamic, related to the context of the task.
Anthology ID:
W19-1608
Volume:
Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Venues:
NAACL | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
71–81
URL:
https://www.aclweb.org/anthology/W19-1608
DOI:
10.18653/v1/W19-1608
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://www.aclweb.org/anthology/W19-1608.pdf
Supplementary:
 W19-1608.Supplementary.pdf