Evaluating parsing strategies using standardized parse files

The availability of large files of manually-reviewed parse trees from the University of Pennsylvania "tree bank", along with a program for comparing system-generated parses against these "standard" parses, provides a new opportunity for evaluating different parsing strategies. We discuss some of the restructuring required to the output of our parser so that it could be meaningfully compared with these standard parses. We then describe several heuristics for improving parsing accuracy and coverage, such as closest attachment of modifiers, statistical grammars, and fitted parses, and present a quantitative evaluation of the improvements obtained with each strategy.