Human evaluation of automatically generated text: Current trends and best practice guidelines

Chris van der Lee, Albert Gatt, Emiel van Miltenburg, Emiel Krahmer

Abstract: Highlights • The current paper provides an overview of human evaluation practices in NLG. • The current paper gives an overview of the steps necessary to undertake a human evaluation study. • Building on findings from NLG, but also statistics and the behavioral sciences, the current paper provides a set of recommendations and best practices for human evaluation in NLG. Abstract Currently, there is little agreement as to how Natural Language Generation (NLG) systems should be evaluated, with a particularly high degree of variation in the way that human evaluation is carried out. This paper provides an overview of how (mostly intrinsic) human evaluation is currently conducted and presents a set of best practices, grounded in the literature. These best practices are also linked to the stages that researchers go through when conducting an evaluation research (planning stage; execution and release stage), and the specific steps in these stages. With this paper, we hope to contribute to the quality and consistency of human evaluations in NLG.