Differentiable Greedy Networks
This addresses the challenge of selecting informative sentence sets for claim verification, offering an incremental improvement over conventional methods that evaluate sentences individually.
The paper tackled the problem of subset selection for claim verification in the FEVER task by proposing a differentiable greedy network that enables gradient-based training while achieving near-optimal performance, outperforming discrete optimization and baseline methods in precision and recall.
Optimal selection of a subset of items from a given set is a hard problem that requires combinatorial optimization. In this paper, we propose a subset selection algorithm that is trainable with gradient-based methods yet achieves near-optimal performance via submodular optimization. We focus on the task of identifying a relevant set of sentences for claim verification in the context of the FEVER task. Conventional methods for this task look at sentences on their individual merit and thus do not optimize the informativeness of sentences as a set. We show that our proposed method which builds on the idea of unfolding a greedy algorithm into a computational graph allows both interpretability and gradient-based training. The proposed differentiable greedy network (DGN) outperforms discrete optimization algorithms as well as other baseline methods in terms of precision and recall.