Developing a hybrid NP parser

Details Developing a hybrid NP parser Developing a hybrid NP parser

1997-04-23

arxiv.org/abs/cmp-lg/9704009v2

Proceedings of 5th ANLP, 1997

Computer Science

Computation and Language

8 pages, uses aclap.sty, epsf.sty

Scientific paper

We describe the use of energy function optimization in very shallow syntactic parsing. The approach can use linguistic rules and corpus-based statistics, so the strengths of both linguistic and statistical approaches to NLP can be combined in a single framework. The rules are contextual constraints for resolving syntactic ambiguities expressed as alternative tags, and the statistical language model consists of corpus-based n-grams of syntactic tags. The success of the hybrid syntactic disambiguator is evaluated against a held-out benchmark corpus. Also the contributions of the linguistic and statistical language models to the hybrid model are estimated.

Affiliated with

Also associated with

No associations

Rating

Developing a hybrid NP parser 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 Developing a hybrid NP parser, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Developing a hybrid NP parser will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-529171