Developing a hybrid NP parser
| dc.creator | Voutilainen, Atro | |
| dc.creator | Padro, Lluis | |
| dc.date | 1997-04-23 | |
| dc.date | 1997-04-24 | |
| dc.date.accessioned | 2026-07-07T09:02:22Z | |
| dc.date.available | 2026-07-07T09:02:22Z | |
| dc.description | 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. | |
| dc.description | 8 pages, uses aclap.sty, epsf.sty | |
| dc.identifier | https://arxiv.org/abs/cmp-lg/9704009 | |
| dc.identifier | http://arxiv.org/abs/cmp-lg/9704009 | |
| dc.identifier | Proceedings of 5th ANLP, 1997 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/148609 | |
| dc.subject | Computation and Language | |
| dc.title | Developing a hybrid NP parser | |
| dc.type | text |