Abstract
Recent work on semantic role labeling (SRL) has focused almost exclusively on the analysis of the predicate-argument structure of verbs, largely due to the lack of human-annotated resources for other types of predicates that can serve as training and test data for the semantic role labeling systems. However, it is well-known that verbs are not the only type of predicates that can take arguments. Most notably, nouns that are nominalized forms of verbs and relational nouns generally are also considered to have their own predicate argument structure. In this paper we report results of SRL experiments on nominalized predicates in Chinese, using a newly completed corpus, the Chinese Nombank. We also discuss the impact of using publicly available manually annotated verb data to improve the SRL accuracy of nouns, exploiting a widely-held assumption that verbs and their nominalizations share the same predicate-argument structure. Finally, we discuss the results of applying reranking techniques to improve SRL accuracy for nominalized predicates, which showed insignificant improvement.