Modeling Semantic Plausibility by Injecting World Knowledge

Su Wang, Greg Durrett, Katrin Erk


Abstract
Distributional data tells us that a man can swallow candy, but not that a man can swallow a paintball, since this is never attested. However both are physically plausible events. This paper introduces the task of semantic plausibility: recognizing plausible but possibly novel events. We present a new crowdsourced dataset of semantic plausibility judgments of single events such as man swallow paintball. Simple models based on distributional representations perform poorly on this task, despite doing well on selection preference, but injecting manually elicited knowledge about entity properties provides a substantial performance boost. Our error analysis shows that our new dataset is a great testbed for semantic plausibility models: more sophisticated knowledge representation and propagation could address many of the remaining errors.
Anthology ID:
N18-2049
Volume:
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)
Month:
June
Year:
2018
Address:
New Orleans, Louisiana
Editors:
Marilyn Walker, Heng Ji, Amanda Stent
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
303–308
Language:
URL:
https://aclanthology.org/N18-2049
DOI:
10.18653/v1/N18-2049
Bibkey:
Cite (ACL):
Su Wang, Greg Durrett, and Katrin Erk. 2018. Modeling Semantic Plausibility by Injecting World Knowledge. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 303–308, New Orleans, Louisiana. Association for Computational Linguistics.
Cite (Informal):
Modeling Semantic Plausibility by Injecting World Knowledge (Wang et al., NAACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/N18-2049.pdf
Note:
 N18-2049.Notes.pdf
Video:
 https://aclanthology.org/N18-2049.mp4
Code
 suwangcompling/Modeling-Semantic-Plausibility-NAACL18