Empirical approach to conceptual case frame acquisition

Conceptual natural language processing systems usually rely on case frame instantiation to recognize events and role objects in text. But generating a good set of case frames for a domain is time-consuming, tedious, and prone to errors of omission. We have developed a corpus-based algorithm for acquiring conceptual case frames empirically from unannotated text. Our algorithm builds on previous research on corpus-based methods for acquiring extraction patterns and semantic lexicons. Given extraction patterns and a semantic lexicon for a domain, our algorithm learns semantic preferences for each extraction pattern and merges the syntactically compatible patterns to produce multi-slot case frames with selectional restrictions. The case frames generate more cohesive output and produce fewer false hits than the original extraction patterns. Our system requires only preclassified training texts and a few hours of manual review to filter the dictionaries, demonstrating that conceptual case frames can be acquired from unannotated text without special training resources.