e task is one of the core concepts around which Information Retrieval (IR) and particularly its evaluation are structured. e traditional search task is a set of instructions that motivate a query and which enable the assessment of the query results' relevance. With the introduction of the user into the evaluation process the task evolved into a set of instructions that the user is provided with when they start the evaluation process. As these tasks become ever more complex the boundary between the IR task and the larger work task that motivates the IR task start to blur. is transition poses a major question for evaluation, as it also blurs the question of whether the evaluation is judging the quality of the IR system, the quality of the data for completing the work task, or the user's ability to identify with and complete the larger work task. In my keynote I will explore some of these issues.
CHIIR 2017 Workshop on Supporting Complex Search Tasks, Oslo, Norway. Copyright for the individual papers remains with the authors. Copying permied for private and academic purposes. is volume is published and copyrighted by its editors. Published on CEUR-WS, Volume 1798, hp://ceur-ws.org/Vol-1798/.