UTDMet: Combining WordNet and corpus data for argument coercion detection

Authors:
Kirk Roberts;Sanda Harabagiu
Affiliations:
University of Texas at Dallas, Richardson, Texas;University of Texas at Dallas, Richardson, Texas
Venue:
SemEval '10 Proceedings of the 5th International Workshop on Semantic Evaluation
Year:
2010

Citing 5
Cited 0

A probabilistic account of logical metonymy

Computational Linguistics
The Proposition Bank: An Annotated Corpus of Semantic Roles

Computational Linguistics
Experiments with interactive question-answering

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Linking FrameNet to the Suggested Upper Merged Ontology

Proceedings of the 2006 conference on Formal Ontology in Information Systems: Proceedings of the Fourth International Conference (FOIS 2006)
SemEval-2010 task 7: argument selection and coercion

DEW '09 Proceedings of the Workshop on Semantic Evaluations: Recent Achievements and Future Directions

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes our system for the classification of argument coercion for SemEval-2010 Task 7. We present two approaches to classifying an argument's semantic class, which is then compared to the predicate's expected semantic class to detect coercions. The first approach is based on learning the members of an arbitrary semantic class using WordNet's hypernymy structure. The second approach leverages automatically extracted semantic parse information from a large corpus to identify similar arguments by the predicates that select them. We show the results these approaches obtain on the task as well as how they can improve a traditional feature-based approach.