HEAD DRIVEN STATISTICAL MODELS FOR NATURAL LANGUAGE PARSING Michael Collins Supervisor Professor Mitch Marcus Statistical models for parsing natural language have recently shown considerable suc cess in broad coverage domains Ambiguity often leads to an input sentence having many possible parse trees statistical approaches assign a probability to each tree thereby rank ing competing trees in or...

A prevalent trend in modeling human sentence processing has been to account for both initial attachment preferences and reanalysis behaviors with minimal extensions to a presumed set of initial parsing operations. Here, an entirely different formulation of the initial attachment and revision processes is suggested. Rather than assuming that all parsing is (as much as possible) initial attachmen...

Abstract Using both offline and online measures, the present study investigates attachment resolution in relative clauses English natives (L1) nonnatives (L2). We test how clause interacts with linguistic factors participant-level individual differences. Previous L1 studies have demonstrated a low preference also an “ambiguity advantage” suggesting that L1ers may not as strong is sometimes clai...

We present a unified generative model of coordination that considers parallelism of conjuncts and selectional preferences. Parallelism of conjuncts, which frequently characterizes coordinate structures, is modeled as a synchronized generation process in the generative parser. Selectional preferences learned from a large web corpus provide an important clue for resolving the ambiguities of coord...

This paper describes a new addition to the family of parsing models based on the principles of Description-Theory (Marcus, Hindle & Fleck, 1983). We demonstrate how the de nition of two simple parsing operations, simple attachment and tree lowering, which are related to the grammatical composition operations of substitution and adjunction in the Tree Adjoining Grammar formalism, yields a parser...

We present a processing model that integrates some important psychological claims about the human sentence parsing mechanism, namely that processing is innuenced by limitations on working memory and by various syntactic preferences. The model uses time-constraint information to resolve connicting preferences in a psychologically plausible way. The starting point for this proposal is the Sausage...