Logical Story Representations via FrameNet + Semantic Parsing

Lane Lawley, Lenhart Schubert


Abstract
We propose a means of augmenting FrameNet parsers with a formal logic parser to obtain rich semantic representations of events. These schematic representations of the frame events, which we call Episodic Logic (EL) schemas, abstract constants to variables, preserving their types and relationships to other individuals in the same text. Due to the temporal semantics of the chosen logical formalism, all identified schemas in a text are also assigned temporally bound “episodes” and related to one another in time. The semantic role information from the FrameNet frames is also incorporated into the schema’s type constraints. We describe an implementation of this method using a neural FrameNet parser, and discuss the approach’s possible applications to question answering and open-domain event schema learning.
Anthology ID:
2022.distcurate-1.3
Volume:
Proceedings of the Workshop on Dimensions of Meaning: Distributional and Curated Semantics (DistCurate 2022)
Month:
July
Year:
2022
Address:
Seattle, Washington
Venue:
DistCurate
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
19–23
Language:
URL:
https://aclanthology.org/2022.distcurate-1.3
DOI:
10.18653/v1/2022.distcurate-1.3
Bibkey:
Cite (ACL):
Lane Lawley and Lenhart Schubert. 2022. Logical Story Representations via FrameNet + Semantic Parsing. In Proceedings of the Workshop on Dimensions of Meaning: Distributional and Curated Semantics (DistCurate 2022), pages 19–23, Seattle, Washington. Association for Computational Linguistics.
Cite (Informal):
Logical Story Representations via FrameNet + Semantic Parsing (Lawley & Schubert, DistCurate 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.distcurate-1.3.pdf
Data
FrameNet