Svetlana Hensman
svetlana.damianova
Department of Computer Science, University College Dublin
John Dunnion
john.dunnion}@ucd.ie
Department of Computer Science, University College Dublin
APPLYING VERBNET FOR AUTOMATIC SEMANTIC ROLE IDENTIFICATION
ABSTRACT
The problem of automatic semantic role identification is an important part of many natural language processing systems and while the performance of the recent syntactic parsers is really high, finding a representation in terms of semantic roles is still unsatisfactory. This paper describes a method for identifying and labelling the semantic roles of a sentence. Our system creates a verb pattern using the parse tree of the sentence and then matches it to the possible semantic frames extracted from the VerbNet lexicon for this verb in order to identify the semantic roles.