Yifan Qiao


2024

pdf bib
Threshold-driven Pruning with Segmented Maximum Term Weights for Approximate Cluster-based Sparse Retrieval
Yifan Qiao | Parker Carlson | Shanxiu He | Yingrui Yang | Tao Yang
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing

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.

2022

pdf bib
Compact Token Representations with Contextual Quantization for Efficient Document Re-ranking
Yingrui Yang | Yifan Qiao | Tao Yang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Transformer based re-ranking models can achieve high search relevance through context- aware soft matching of query tokens with document tokens. To alleviate runtime complexity of such inference, previous work has adopted a late interaction architecture with pre-computed contextual token representations at the cost of a large online storage. This paper proposes contextual quantization of token embeddings by decoupling document-specific and document-independent ranking contributions during codebook-based compression. This allows effective online decompression and embedding composition for better search relevance. This paper presents an evaluation of the above compact token representation model in terms of relevance and space efficiency.