The memory-based parsing or pattern-based phrase recognition has been successfully applied to the information extraction f r o m natural language corpus. O n e problem o f s u c h an approach is that the parser needs a very large number of semantic patterns. Manual creation of the semantic patterns is unrealistic. T o solve the scalability and poriability problem, automatic acquisition of semantic patterns must be provided. In this paper, a semi-automatic knowledge acquisition system, PALKA, is presented, which facilitates the construction of a large knowledge base of semantic patterns. The system acquires semantic patterns f r o m texts with a small amount of user interaction. The acquisition process with PALKA is described in detail, and a prelimina y experimental result is discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.