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...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-06
Main Authors: Qiao, Yifan, Yang, Yingrui, He, Shanxiu, Yang, Tao
Format: Article
Language:English
Subjects:
Documents
Representations
Retrieval
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422
DOI:10.48550/arxiv.2306.11293