Three Generative, Lexicalised Models for Statistical Parsing

dc.creatorCollins, Michael
dc.date1997-06-17
dc.date.accessioned2026-07-07T09:10:52Z
dc.date.available2026-07-07T09:10:52Z
dc.descriptionIn 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.description8 pages, to appear in Proceedings of ACL/EACL 97.
dc.identifierhttps://arxiv.org/abs/cmp-lg/9706022
dc.identifierhttp://arxiv.org/abs/cmp-lg/9706022
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151481
dc.subjectComputation and Language
dc.titleThree Generative, Lexicalised Models for Statistical Parsing
dc.typetext

Files

Collections