1999/07/08 by John Carroll, Guido Minnen, Ted Briscoe
Computer Science · #cs.CL
published as Proceedings of the EACL99 workshop on Linguistically Interpreted Corpora (LINC), Bergen, Norway, June 12 · 7 pages, LaTeX (uses eaclap.sty)
arxiv created 1999/07/08 · arxiv updated 2009/11/30
We describe a recently developed corpus annotation scheme for evaluating parsers that avoids shortcomings of current methods. The scheme encodes grammatical relations between heads and dependents, and has been used to mark up a new public-domain corpus of naturally occurring English text. We show how the corpus can be used to evaluate the accuracy of a robust parser, and relate the corpus to extant resources.