Three Generative, Lexicalised Models for Statistical Parsing
| dc.creator | Collins, Michael | |
| dc.date | 1997-06-17 | |
| dc.date.accessioned | 2026-07-07T09:10:52Z | |
| dc.date.available | 2026-07-07T09:10:52Z | |
| dc.description | In this paper we first propose a new statistical parsing model, which is a generative model of lexicalised context-free grammar. We then extend the model to include a probabilistic treatment of both subcategorisation and wh-movement. Results on Wall Street Journal text show that the parser performs at 88.1/87.5% constituent precision/recall, an average improvement of 2.3% over (Collins 96). | |
| dc.description | 8 pages, to appear in Proceedings of ACL/EACL 97. | |
| dc.identifier | https://arxiv.org/abs/cmp-lg/9706022 | |
| dc.identifier | http://arxiv.org/abs/cmp-lg/9706022 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/151481 | |
| dc.subject | Computation and Language | |
| dc.title | Three Generative, Lexicalised Models for Statistical Parsing | |
| dc.type | text |