Learning Transformation Rules to Find Grammatical Relations

Simple item page
dc.creatorFerro, Lisa
dc.creatorVilain, Marc
dc.creatorYeh, Alexander
dc.date1999-06-14
dc.date.accessioned2026-07-07T03:24:09Z
dc.date.available2026-07-07T03:24:09Z
dc.descriptionGrammatical relationships are an important level of natural language processing. We present a trainable approach to find these relationships through transformation sequences and error-driven learning. Our approach finds grammatical relationships between core syntax groups and bypasses much of the parsing phase. On our training and test set, our procedure achieves 63.6% recall and 77.3% precision (f-score = 69.8).
dc.description10 pages. Uses latex-acl.sty and named.sty
dc.identifierhttps://arxiv.org/abs/cs/9906015
dc.identifierhttp://arxiv.org/abs/cs/9906015
dc.identifierComputational Natural Language Learning (CoNLL-99), pages 43-52, June, 1999. Bergen, Norway
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/33215
dc.subjectComputation and Language
dc.subjectI.2.7
dc.titleLearning Transformation Rules to Find Grammatical Relations
dc.typetext

Files

Collections

arXiv