This is an efficient SPLADE model from NAVER designed for sparse vector retrieval. It supports query and document expansion using a bag-of-words approach and knowledge distillation. The model is built on BERT architecture and is suitable for researchers working on passage retrieval and search systems. It is available for use with the Transformers library.
In the Foundation models & chat space, Efficient Splade VI BT Large Query takes a focused approach. It focuses on improving search relevance through sparse lexical representations and query/document expansion in retrieval systems. It is built as an open-source project for information retrieval researchers and engineers. Efficient Splade VI BT Large Query is open source under the Open Source license. Efficient Splade VI BT Large Query is available on the web, the command line, and API.
Behind Efficient Splade VI BT Large Query is NAVER, and the product first shipped in 2021. Development happens publicly on GitHub with 999 stars. Key capabilities include Sparse Retrieval, Query Expansion, and Document Expansion.
Latest indexed changes and source events
naver/efficient-splade-VI-BT-large-query verified by the PulseGate indexer
Other apps tracked under the same category.
