Efficient Neural Ranking Using Forward Indexes

Abstract

Neural document ranking approaches, specifically transformer models, have achieved impressive gains in ranking performance. However, query processing using such over-parameterized models is both resource and time intensive. In this paper, we propose the Fast-Forward index -- a simple vector forward index that facilitates ranking documents using interpolation of lexical and semantic scores -- as a replacement for contextual re-rankers and dense indexes based on nearest neighbor search. Fast-Forward indexes rely on efficient sparse models for retrieval and merely look up pre-computed dense transformer-based vector representations of documents and passages in constant time for fast CPU-based semantic similarity computation during query processing. We propose index pruning and theoretically grounded early stopping techniques to improve the query processing throughput. We conduct extensive large-scale experiments on TREC-DL datasets and show improvements over hybrid indexes in performance a

Stats

• citations14
• S2 citations—
• github stars0
• HF likes0
• heat score8.82
• arxiv keyleonhardt2021efficient

Related papers

• Efficient Neural Ranking Using Forward Indexes And Lightweight Encoders (2023)5.24
• Improving Neural Ranking Models With Traditional IR Methods (2023)0.00
• SDR: Efficient Neural Re-ranking Using Succinct Document Representation (2021)3.58
• GUITAR: Gradient Pruning Toward Fast Neural Ranking (2023)2.26
• Neural Ranking Models For Document Retrieval (2021)11.08
• Faster Learned Sparse Retrieval With Guided Traversal (2022)11.29
• Efficient And Effective Tree-based And Neural Learning To Rank (2023)9.03
• Quality And Cost Trade-offs In Passage Re-ranking Task (2021)0.00