Representation Sparsification with Hybrid Thresholding for Fast SPLADE-based Document Retrieval

06/20/2023

∙

by   Yifan Qiao, et al.

∙

0

∙

share

Learned sparse document representations using a transformer-based neural model has been found to be attractive in both relevance effectiveness and time efficiency. This paper describes a representation sparsification scheme based on hard and soft thresholding with an inverted index approximation for faster SPLADE-based document retrieval. It provides analytical and experimental results on the impact of this learnable hybrid thresholding scheme.