In this talk I will be focusing on techniques which may improve parser performance for so-called deep linguistic grammars. Most notably, I will present an innovative chart mining technique for improving parse coverage based on partial parse outputs from precision grammars. The general approach of mining features from partial analyses is applicable to a range of lexical acquisition tasks, and is particularly suited to domain-specific lexical tuning and lexical acquisition using low coverage grammars. As an illustration of the functionality of the proposed technique, I will show a lexical acquisition model developed for English verb particle constructions which operates over unlexicalised features mined from a partial parsing chart. The proposed technique is shown to outperform a state-of-the-art parser over the target task, despite being based
on relatively simplistic features.
