Probabilistic Models of Verb-Argument Structure

We evaluate probabilistic models of verb argument structure trained on a corpus of verbs and their syntactic arguments. Models designed to represent patterns of verb alternation behavior are compared with generic clustering models in terms of the perplexity assigned to held-out test data. While the specialized models of alternation do not perform as well, closer examination reveals alternation behavior represented implicitly in the generic models.

• Type: Journal
• Year: 2002
• Where: COLING
• Authors: Daniel Gildea
• Keywords: Alternation Behavior, COLING 2002, COLING 2008, Generic Clustering Models, Probabilistic Models