Towards History-based Grammars: Using Richer Models for Probabilistic Parsing

Details Towards History-based Grammars: Using Richer Models for Probabilistic Parsing Towards History-based Grammars: Using Richer Models for Probabilistic Parsing

1994-05-03

arxiv.org/abs/cmp-lg/9405007v1

Proceedings, DARPA Speech and Natural Language Workshop, 1992

Computer Science

Computation and Language

6 pages

Scientific paper

We describe a generative probabilistic model of natural language, which we call HBG, that takes advantage of detailed linguistic information to resolve ambiguity. HBG incorporates lexical, syntactic, semantic, and structural information from the parse tree into the disambiguation process in a novel way. We use a corpus of bracketed sentences, called a Treebank, in combination with decision tree building to tease out the relevant aspects of a parse tree that will determine the correct parse of a sentence. This stands in contrast to the usual approach of further grammar tailoring via the usual linguistic introspection in the hope of generating the correct parse. In head-to-head tests against one of the best existing robust probabilistic parsing models, which we call P-CFG, the HBG model significantly outperforms P-CFG, increasing the parsing accuracy rate from 60% to 75%, a 37% reduction in error.

Affiliated with

Also associated with

No associations

Rating

Towards History-based Grammars: Using Richer Models for Probabilistic 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 Towards History-based Grammars: Using Richer Models for Probabilistic Parsing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Towards History-based Grammars: Using Richer Models for Probabilistic Parsing will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-8794