Three Generative, Lexicalised Models for Statistical Parsing

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).

• Type: Conference
• Year: 1997
• Where: ACL
• Authors: Michael Collins
• Keywords: ACL 1997, ACL 2007, Generative Model, Statistical Parsing Model, Wall Street Journal