A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systems

11/08/2020

∙

by   Craig Thomson, et al.

∙

0

∙

share

Most Natural Language Generation systems need to produce accurate texts. We propose a methodology for high-quality human evaluation of the accuracy of generated texts, which is intended to serve as a gold-standard for accuracy evaluations of data-to-text systems. We use our methodology to evaluate the accuracy of computer generated basketball summaries. We then show how our gold standard evaluation can be used to validate automated metrics