Lexicon acquisition: learning from corpus by capitalizing on lexical categories
Uri Zernik · 1989
Text examples must be exploited in the acquisition of lexical structures. However, neither syntactic nor semantic features are provided by the text itself, and so acquisition must be aided by additional resources. We investigate the application of an existing resource, a set of lexical categories, as a prediction method. We present an algorithm that applies (a) top-down prediction based on lexical categories; (b) bottom-up validation by scanning text examples. Finally, we discuss the issue of semantic bootstrapping and identify its theoretical and practical limitations. 1