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).

Extracted Key Phrases

8 Figures and Tables

Citations per Year

1,113 Citations

Semantic Scholar estimates that this publication has 1,113 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Collins1997ThreeGL, title={Three Generative, Lexicalised Models for Statistical Parsing}, author={Michael Collins}, booktitle={ACL}, year={1997} }