Three Generative, Lexicalised Models for Statistical Parsing

Details Three Generative, Lexicalised Models for Statistical Parsing Three Generative, Lexicalised Models for Statistical Parsing

1997-06-17

arxiv.org/abs/cmp-lg/9706022v1

Computer Science

Computation and Language

8 pages, to appear in Proceedings of ACL/EACL 97.

Scientific paper

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).

Affiliated with

Also associated with

No associations

Rating

Three Generative, Lexicalised Models for Statistical Parsing does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Three Generative, Lexicalised Models for Statistical Parsing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Three Generative, Lexicalised Models for Statistical Parsing will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-516675