Learning Unification-Based Grammars and the Treatment of Undergeneration

We present a framework for learning plausible unification-based natural language grammars. Our framework uses both modelbased and data-driven learning without being committed to any particular configuration of these two learning schemes. We use learning to overcome the problem of undergeneration in natural language grammars. This paper presents work that is still in progress: the model-based learning component has been built but the data-driven learning component has not. Full evaluation of the framework awaits a complete implementation. 1 Introduction 1.1 Undergeneration An application of learning natural language grammars is the treatment of undergeneration. A grammar undergenerates when it fails to generate some sentence which human informants judge to be grammatical. Undergeneration undermines the successful processing of natural language. Consider the grammar: S ! NP VP NP ! Det N1 VP ! V NP N1 ! N0 NP ! N1 Sam : NP chases : V the : Det happy : Adj cat : N0 This grammar ..