2024
Threshold-driven Pruning with Segmented Maximum Term Weights for Approximate Cluster-based Sparse Retrieval
EMNLP 2024main
This paper revisits dynamic pruning through rank score thresholding in cluster-based sparse retrieval to skip the index partially at cluster and document levels during inference. It proposes a two-parameter pruning control scheme called ASC with a probabilistic guarantee on rank-safeness competitive…