Three Generative, Lexicalised Models for Statistical Parsing

TL;DR

This paper introduces a new generative lexicalized parsing model that incorporates subcategorization and wh-movement, achieving improved accuracy on Wall Street Journal data.

Contribution

It presents a novel generative lexicalized parsing model with probabilistic handling of syntactic phenomena, enhancing parsing performance.

Findings

Achieves 88.1% precision and 87.5% recall on WSJ data

Improves over previous models by 2.3% in accuracy

Incorporates probabilistic treatment of subcategorisation and wh-movement

Abstract

In this paper we first propose a new statistical parsing model, which is a generative model of lexicalised context-free grammar. We then extend the model to include a probabilistic treatment of both subcategorisation and wh-movement. Results on Wall Street Journal text show that the parser performs at 88.1/87.5% constituent precision/recall, an average improvement of 2.3% over (Collins 96).