1999/06/14 by Lisa Ferro, Marc Vilain, Alexander Yeh
Computer Science · #cs.CL
published as Computational Natural Language Learning (CoNLL-99), pages 43-52, June, 1999. Bergen, Norway · 10 pages. Uses latex-acl.sty and named.sty
arxiv created 1999/06/14 · arxiv updated 2009/11/30
Grammatical 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).