naver/splade
SPLADE: sparse neural search (SIGIR21, SIGIR22)
This project helps information retrieval specialists and search engineers build highly effective search systems. It takes text documents and search queries as input, processing them to produce optimized search results that are both relevant and efficient to retrieve. The output is a refined ranking of documents, making it easier for users to find what they're looking for, particularly in large and diverse datasets.
984 stars. No commits in the last 6 months.
Use this if you need to improve the relevance and efficiency of your search engine's initial ranking of documents, especially when dealing with large volumes of text and complex queries.
Not ideal if you are looking for a simple keyword-matching tool or a system for very small, niche datasets where traditional search methods are sufficient.
Stars
984
Forks
94
Language
Python
License
—
Category
Last pushed
May 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/naver/splade"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
smart-on-fhir/cumulus-etl
Extract FHIR data, Transform with NLP and DEID tools, and then Load FHIR data into a SQL...
mirkosertic/FXDesktopSearch
A JavaFX based desktop search application.
opensemanticsearch/open-semantic-search
Open Source research tool to search, browse, analyze and explore large document collections by...
opensemanticsearch/open-semantic-etl
Python based Open Source ETL tools for file crawling, document processing (text extraction,...
opensemanticsearch/open-semantic-entity-search-api
Open Source REST API for named entity extraction, named entity linking, named entity...