Event Representation through Semantic Roles: Evaluation of Coverage
Aliaksandr Huminski, Hao Zhang

TL;DR
This paper evaluates the coverage of semantic role theory in event representation, highlighting its limitations and proposing a hybrid role-scalar approach based on empirical analysis.
Contribution
It provides empirical evidence of the insufficiency of pure semantic role theory and introduces a hybrid approach for better event representation.
Findings
Semantic role theory is necessary but not sufficient for complete event representation.
Empirical analysis supports the need for a hybrid role-scalar approach.
Preliminary results suggest improved coverage with the proposed method.
Abstract
Semantic role theory is a widely used approach for event representation. Yet, there are multiple indications that semantic role paradigm is necessary but not sufficient to cover all elements of event structure. We conducted an analysis of semantic role representation for events to provide an empirical evidence of insufficiency. The consequence of that is a hybrid role-scalar approach. The results are considered as preliminary in investigation of semantic roles coverage for event representation.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Semantic Web and Ontologies
