Learned sparse retrieval

id: learned-sparse-retrieval-269-11157313
title: Learned sparse retrieval
text: Learned sparse retrieval or sparse neural search is an approach to text search which uses a sparse vector representation of queries and documents. It borrows techniques both from lexical bag-of-words and vector embedding algorithms, and is claimed to perform better than either alone. The best-known sparse neural search systems are SPLADE and its successor SPLADE v2. Others include DeepCT, uniCOIL, EPIC, DeepImpact, TILDE and TILDEv2, Sparta, SPLADE-max, and DistilSPLADE-max. Some implementations
brand slug: wiki
category slug: encyclopedia
description: Document search algorithm
original url: https://en.wikipedia.org/wiki/Learned_sparse_retrieval
date created:
date modified: 2024-04-19T07:58:51Z
main entity: {"identifier":"Q122363545","url":"https://www.wikidata.org/entity/Q122363545"}
image:
fields total: 13
integrity: 14

Related Entries

Explore Next Part