Lexical Patterns or Dependency Patterns: Which Is Better for Hypernym Extraction?

We compare two different types of extraction patterns for automatically deriving semantic information from text: lexical patterns, built from words and word class information, and dependency patterns with syntactic information obtained from a full parser. We are particularly interested in whether the richer linguistic information provided by a parser allows for a better performance of subsequent information extraction work. We evaluate automatic extraction of hypernym information from text and conclude that the application of dependency patterns does not lead to substantially higher precision and recall scores than using lexical patterns.