Threshold-driven Pruning with Segmented Maximum Term Weights for Approximate Cluster-based Sparse Retrieval
Abstract: 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 competitiveness. ASC uses cluster-level maximum weight segmentation to improve accuracy of rank score bound estimation and threshold-driven pruning, and is targeted for speeding up retrieval applications requiring high relevance competitiveness. The experiments with MS MARCO and BEIR show that ASC improves the accuracy and safeness of pruning for better relevance while delivering a low latency on a single-threaded CPU.
Paper Type: Long
Research Area: Information Retrieval and Text Mining
Research Area Keywords: cluster-based text retrieval, learned sparse representations, dynamic index pruning, approximation and rank-safeness
Contribution Types: Approaches low compute settings-efficiency
Languages Studied: English
Submission Number: 4052
Loading