Multi-winner Approval Voting Goes Epistemic
This addresses aggregation challenges in multi-label annotation tasks, but it is incremental as it extends epistemic voting to multi-winner contexts.
The paper tackles the problem of aggregating multi-label annotations with known bounds on the true set size by modeling votes as noisy signals and defining optimal rules, reporting experiments on collected data.
Epistemic voting interprets votes as noisy signals about a ground truth. We consider contexts where the truth consists of a set of objective winners, knowing a lower and upper bound on its cardinality. A prototypical problem for this setting is the aggre-gation of multi-label annotations with prior knowledge on the size of the ground truth. We posit noisemodels, for which we define rules that output an optimal set of winners. We report on experiments on multi-label annotations (which we collected).