Papers by Shanxiu He

1 papers
Threshold-driven Pruning with Segmented Maximum Term Weights for Approximate Cluster-based Sparse Retrieval (2024.emnlp-main)

Copied to clipboard

Challenge: Using rank score thresholding, sparse retrieval skips the index at cluster and document levels.
Approach: They propose a pruning control scheme with a probabilistic guarantee on rank-safeness competitiveness.
Outcome: The proposed pruning control scheme improves accuracy and safeness while delivering low latency on single-threaded CPU.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations