Towards Verifying Semantic Roles Co-occurrence
Aliaksandr Huminski, Hao Zhang, Gangeshwar Krishnamurthy

TL;DR
This paper investigates the co-occurrence of semantic roles in verb representations, revealing hidden restrictions on role combinations through analysis of VerbNet, which impacts semantic role theory and NLP applications.
Contribution
It introduces an evidence-based approach to identify restrictions on semantic role co-occurrence using VerbNet data, challenging the assumption of universal role combinations.
Findings
Semantic roles co-occur in verb representations.
Hidden restrictions on role combinations are identified.
Implications for semantic role theory and NLP are discussed.
Abstract
Semantic role theory considers roles as a small universal set of unanalyzed entities. It means that formally there are no restrictions on role combinations. We argue that the semantic roles co-occur in verb representations. It means that there are hidden restrictions on role combinations. To demonstrate that a practical and evidence-based approach has been built on in-depth analysis of the largest verb database VerbNet. The consequences of this approach are considered.
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
