Representation Sparsification With Hybrid Thresholding For Fast Splade-based Document Retrieval
Yifan Qiao, Yingrui Yang, Shanxiu He, Tao Yang . Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval 2023 – 7 citations
[Paper]
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.