About This Document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Thibault Formal
- sl:arxiv_num : 2107.05720
- sl:arxiv_published : 2021-07-12T20:17:44Z
- sl:arxiv_summary : In neural Information Retrieval, ongoing research is directed towards
improving the first retriever in ranking pipelines. Learning dense embeddings
to conduct retrieval using efficient approximate nearest neighbors methods has
proven to work well. Meanwhile, there has been a growing interest in learning
sparse representations for documents and queries, that could inherit from the
desirable properties of bag-of-words models such as the exact matching of terms
and the efficiency of inverted indexes. In this work, we present a new
first-stage ranker based on explicit sparsity regularization and a
log-saturation effect on term weights, leading to highly sparse representations
and competitive results with respect to state-of-the-art dense and sparse
methods. Our approach is simple, trained end-to-end in a single stage. We also
explore the trade-off between effectiveness and efficiency, by controlling the
contribution of the sparsity regularization.@en
- sl:arxiv_title : SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking@en
- sl:arxiv_updated : 2021-07-12T20:17:44Z
- sl:bookmarkOf : https://arxiv.org/abs/2107.05720
- sl:creationDate : 2023-05-18
- sl:creationTime : 2023-05-18T16:54:27Z
Documents with similar tags (experimental)
Preferences...