Corpus Annotation for Parser Evaluation

Carroll, John; Minnen, Guido; Briscoe, Ted

Corpus Annotation for Parser Evaluation

Authors

Carroll, John

Minnen, Guido

Briscoe, Ted

Description

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.
7 pages, LaTeX (uses eaclap.sty)