centering theory

Task decomposition framework for reducing inferential load in structured annotation

A new arXiv preprint proposes decomposing complex structured annotation tasks into sub-tasks to reduce aggregate inferential load across heterogeneous annotator pools that mix human experts and models. The authors introduce a formal model of inferential load grounded in centering theory, using 'centers' (salient anchor entities) to constrain output space complexity. They provide decomposition guidelines and a budget-aware sub-task allocation procedure, with cost-efficiency gains demonstrated from prior work.