Human evaluation of a German surface realisation ranker

Abstract

In this paper we present a human-based evaluation of surface realisation alternatives. We examine the relative rankings of naturally occurring corpus sentences and automatically generated strings chosen by statistical models (language model, loglinear model), as well as the naturalness of the strings chosen by the log-linear model. We also investigate to what extent preceding context has an effect on choice. We show that native speakers do accept quite some variation in word order, but there are also clearly factors that make certain realisation alternatives more natural.