A Flexible POS tagger Using an Automatically Acquired Language Model

Simple item page
dc.creatorMarquez, Lluis
dc.creatorPadro, Lluis
dc.date1997-07-11
dc.date.accessioned2026-07-07T09:10:53Z
dc.date.available2026-07-07T09:10:53Z
dc.descriptionWe present an algorithm that automatically learns context constraints using statistical decision trees. We then use the acquired constraints in a flexible POS tagger. The tagger is able to use information of any degree: n-grams, automatically learned context constraints, linguistically motivated manually written constraints, etc. The sources and kinds of constraints are unrestricted, and the language model can be easily extended, improving the results. The tagger has been tested and evaluated on the WSJ corpus.
dc.description8 pages, aclap.sty, 2 eps figures. Appears in (E)ACL'97
dc.identifierhttps://arxiv.org/abs/cmp-lg/9707003
dc.identifierhttp://arxiv.org/abs/cmp-lg/9707003
dc.identifierProceedings of EACL/ACL 1997, Madrid, Spain
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151491
dc.subjectComputation and Language
dc.titleA Flexible POS tagger Using an Automatically Acquired Language Model
dc.typetext

Files

Collections

arXiv