Deep linguistic analysis for the accurate identification of predicate-argument relations

Abstract

This paper evaluates the accuracy of HPSG parsing in terms of the identification of predicate-argument relations. We could directly compare the output of HPSG parsing with PropBank annotations, by assuming a unique mapping from HPSG semantic representation into PropBank annotation. Even though PropBank was not used for the training of a disambiguation model, an HPSG parser achieved the accuracy competitive with existing studies on the task of identifying PropBank annotations.