Developing a hybrid NP parser

dc.creatorVoutilainen, Atro
dc.creatorPadro, Lluis
dc.date1997-04-23
dc.date1997-04-24
dc.date.accessioned2026-07-07T09:02:22Z
dc.date.available2026-07-07T09:02:22Z
dc.descriptionWe 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.
dc.description8 pages, uses aclap.sty, epsf.sty
dc.identifierhttps://arxiv.org/abs/cmp-lg/9704009
dc.identifierhttp://arxiv.org/abs/cmp-lg/9704009
dc.identifierProceedings of 5th ANLP, 1997
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/148609
dc.subjectComputation and Language
dc.titleDeveloping a hybrid NP parser
dc.typetext

Files

Collections