Dimensions of Transparency in NLP Applications

Broader transparency in descriptions of and communication regarding AI systems is widely considered desirable. This is particularly the case in discussions of fairness and accountability in systems exposed to the general public. However, previous work has suggested that a trade-off exists between greater system transparency and user confusion, where `too much information' clouds a reader's understanding of what a system description means. Unfortunately, transparency is a nebulous concept, difficult to both define and quantify. In this work we address these two issues by proposing a framework for quantifying transparency in system descriptions and apply it to analyze the trade-off between transparency and end-user confusion using NLP conference abstracts.