Probabilistic Tree-Adjoining Grammar as a Framework for Statistical Natural Language Processing

In this paper, I argue for the use of a probabilistic form of tree-adjoining grammar (TAG) in statistical natural language processing. I first discuss two previous statistical approaches --- one that concentrates on the probabilities of structural operations, and another that emphasizes co-occurrence relationships between words. I argue that a purely structural apprach, exemplified by probabilistic context-free grammar, lacks sufficient sensitivity to lexical context, and, conversely, that lexical co-occurence analyses require a richer notion of locality that is best provided by importing some notion of structure.I then propose probabilistic TAG as a framework for statistical language modelling, arguing that it provides an advantageous combination of structure, locality, and lexical sensitivity. Issues in the acquisition of probabilistic TAG and parameter estimation are briefly considered.