Probabilistic Parsing Using Left Corner Language Models

Details Probabilistic Parsing Using Left Corner Language Models Probabilistic Parsing Using Left Corner Language Models

1997-11-17

arxiv.org/abs/cmp-lg/9711003v1

Proceedings of the Fifth International Workshop on Parsing Technologies, MIT, Boston MA, 1997

Computer Science

Computation and Language

12 pages, uses iwpt97.sty

Scientific paper

We introduce a novel parser based on a probabilistic version of a left-corner parser. The left-corner strategy is attractive because rule probabilities can be conditioned on both top-down goals and bottom-up derivations. We develop the underlying theory and explain how a grammar can be induced from analyzed data. We show that the left-corner approach provides an advantage over simple top-down probabilistic context-free grammars in parsing the Wall Street Journal using a grammar induced from the Penn Treebank. We also conclude that the Penn Treebank provides a fairly weak testbed due to the flatness of its bracketings and to the obvious overgeneration and undergeneration of its induced grammar.

Affiliated with

Also associated with

No associations

Rating

Probabilistic Parsing Using Left Corner Language Models 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 Probabilistic Parsing Using Left Corner Language Models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Probabilistic Parsing Using Left Corner Language Models will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-500792