Efficient computation of confidence intervals forword error rates

Word error rate is a standard measure of quality for different tasks such as speech recognition, OCR or machine translation. As such, it is important to compute it together with confidence intervals. Previous works in the literature employ Monte Carlo methods in order to compute those intervals. We show how to compute them without simulations. We also adapt a method that compares two systems over the same test data so that it can be used without simulations.