Densifying Sparse Representations For Passage Retrieval By Representational Slicing

Abstract

Learned sparse and dense representations capture different successful approaches to text retrieval and the fusion of their results has proven to be more effective and robust. Prior work combines dense and sparse retrievers by fusing their model scores. As an alternative, this paper presents a simple approach to densifying sparse representations for text retrieval that does not involve any training. Our densified sparse representations (DSRs) are interpretable and can be easily combined with dense representations for end-to-end retrieval. We demonstrate that our approach can jointly learn sparse and dense representations within a single model and then combine them for dense retrieval. Experimental results suggest that combining our DSRs and dense representations yields a balanced tradeoff between effectiveness and efficiency.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylin2021densifying

Related papers

• Decoding Dense Embeddings: Sparse Autoencoders For Interpreting And Discretizing Dense Retrieval (2025)0.00
• Investigating Multi-layer Representations For Dense Passage Retrieval (2025)0.00
• Pseudo-relevance Feedback For Multiple Representation Dense Retrieval (2021)12.93
• LIDER: An Efficient High-dimensional Learned Index For Large-scale Dense Passage Retrieval (2022)0.00
• Sparse And Dense Retrievers Learn Better Together: Joint Sparse-dense Optimization For Text-image Retrieval (2025)0.00
• Blending Learning To Rank And Dense Representations For Efficient And Effective Cascades (2025)0.00
• Gnn-encoder: Learning A Dual-encoder Architecture Via Graph Neural Networks For Dense Passage Retrieval (2022)4.52
• Interpreting Dense Retrieval As Mixture Of Topics (2021)0.00