Skip to Main content Skip to Navigation
Conference papers

SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking

Abstract : 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-ofthe-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. CCS CONCEPTS • Information systems → Language models.
Document type :
Conference papers
Complete list of metadata
Contributor : HAL Sorbonne Université 5 Gestionnaire Connect in order to contact the contributor
Submitted on : Monday, July 19, 2021 - 2:51:04 PM
Last modification on : Sunday, June 26, 2022 - 3:11:02 AM
Long-term archiving on: : Wednesday, October 20, 2021 - 6:54:23 PM


Publication funded by an institution



Thibault Formal, Benjamin Piwowarski, Stéphane Clinchant. SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking. SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2021, Virtual Event, Canada. pp.2288-2292, ⟨10.1145/3404835.3463098⟩. ⟨hal-03290774⟩



Record views


Files downloads