Developing a hybrid NP parser
cmp-lg
2008-02-03 v2 Computation and Language
Abstract
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.
Cite
@article{arxiv.cmp-lg/9704009,
title = {Developing a hybrid NP parser},
author = {Atro Voutilainen and Lluis Padro},
journal= {arXiv preprint arXiv:cmp-lg/9704009},
year = {2008}
}
Comments
8 pages, uses aclap.sty, epsf.sty