Argument structure analysis of event nouns based on noun-verb co-occurrences and noun phrase patterns
Mamoru Komachi · Institutional Repositories DataBase (IRDB) · 2007
The study of predicate-argument structure analysis has focused largely on verbs and adjectives. However, to fully understand a sentence such as “His decision was right,” both the predicate “was right” and verbal noun “decision” need to be identified as event denoting expressions. Here, we call verbal nouns event nouns, which refer to events like “he decided something,” and propose argument structure analysis of event nouns. Some event nouns, such as “cook”, do not always refer to an event and word sense disambiguation of event nouns has to be done depending on event nouns in use. In this thesis, we present a machine learning method to identify eventness using noun-verb co-occurrences and noun phrase patterns from large corpora. We also investigate a method of incorporating noun-verb co-occurrences to label arguments of event nouns, and conduct error analysis for the argument labeling task.