Nov 2, 2023 · Our framework enables re-ranking at very high retrieval depths and combines the merits of both lexical and semantic matching via score ...

We propose a selective document encoder that dynamically identifies irrelevant document tokens and drops them prior to indexing, reducing index maintenance cost ...

Our framework enables re-ranking at very high retrieval depths and combines the merits of both lexical and semantic matching via score interpolation.

Apr 25, 2022 · In this paper, we propose the Fast-Forward index – a simple vector forward index that facilitates ranking documents using interpolation of ...

The Fast-Forward index is proposed – a simple vector forward index that facilitates ranking documents using interpolation of lexical and semantic scores ...

2024 Efficient Neural Ranking Using Forward Indexes and Lightweight Encoders Jurek Leonhardt, Henrik Müller, Koustav Rudra , and 3 more authors

We propose Fast-Forward indexes - vector forward indexes which exploit the semantic matching capabilities of dual-encoder models for efficient and effective re ...

Apr 4, 2022 · The aim of this paper is to propose an efficient end-to-end ap- proach for ranking long documents without compromising effec- tiveness. Firstly, ...

We perform evaluation to show the effectiveness and efficiency of Fast-Forward indexes—our method has low latency and achieves competitive results without the ...

Dual-encoder-based dense retrieval models have become the standard in IR. They employ large Transformer-based language models, which are notoriously ...