Evaluating Embedded Parsers

Will Fitzgerald and Christopher K. Riesbeck

We need to build parsers that are robust in the face of many types of parsing challenges, and evaluate them for the accuracy and transparency of their results, and how well the parser scales up to practically-sized problems. We describe a number of ways to measure accuracy, transparency and scale-up, in the context of evaluating the parser in the Casper system, a tutorial for training customer service representatives in complex problem solving.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.