Augmented Test Collections: A Step in the Right Direction
This addresses the problem of oversimplified evaluation in information retrieval for researchers and practitioners, but it is incremental as it builds on existing test collection methods.
The authors argue that relevance assessments in IR system evaluation are oversimplified and propose augmenting test collections with contextual and subjective factors from human assessors to enable more realistic, user-focused evaluation.
In this position paper we argue that certain aspects of relevance assessment in the evaluation of IR systems are oversimplified and that human assessments represented by qrels should be augmented to take account of contextual factors and the subjectivity of the task at hand. We propose enhancing test collections used in evaluation with information related to human assessors and their interpretation of the task. Such augmented collections would provide a more realistic and user-focused evaluation, enabling us to better understand the evaluation process, the performance of systems and user interactions. A first step is to conduct user studies to examine in more detail what people actually do when we ask them to judge the relevance of a document.