Representation Sparsification with Hybrid Thresholding for Fast SPLADE-based Document Retrieval
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.
Code (1)
Tasks
RetrievalSimilar Papers 제목 키워드 기반
CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification
Deploying large language models (LLMs) on edge devices presents significant challenges due to the substantial computational overhead and memory requirements. Activation sparsification can mitigate these resource challeng…
An Alternative to FLOPS Regularization to Effectively Productionize SPLADE-Doc
Learned Sparse Retrieval (LSR) models encode text as weighted term vectors, which need to be sparse to leverage inverted index structures during retrieval. SPLADE, the most popular LSR model, uses FLOPS regularization to…
RetrievalExact Hybrid Covariance Thresholding for Joint Graphical Lasso
This paper considers the problem of estimating multiple related Gaussian graphical models from a $p$-dimensional dataset consisting of different classes. Our work is based upon the formulation of this problem as group gr…
Exploring the Representation Power of SPLADE Models
The SPLADE (SParse Lexical AnD Expansion) model is a highly effective approach to learned sparse retrieval, where documents are represented by term impact scores derived from large language models. During training, SPLAD…
RetrievalThe Role of Vocabularies in Learning Sparse Representations for Ranking
Learned Sparse Retrieval (LSR) such as SPLADE has growing interest for effective semantic 1st stage matching while enjoying the efficiency of inverted indices. A recent work on learning SPLADE models with expanded vocabu…