A Gold Standard Methodology for Evaluating Accuracy in Data-To-Text Systems
arXiv:2011.03992
Abstract
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
To appear in INLG-2020. Resources available at https://github.com/nlgcat/evaluating_accuracy