Abstract | ||
---|---|---|
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 and query processing efficiency using only CPUs. Fast-Forward indexes can provide superior ranking performance using interpolation due to the complementary benefits of lexical and semantic similarities. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1145/3485447.3511955 | International World Wide Web Conference |
Keywords | DocType | Citations |
retrieval, dense, sparse, ranking, interpolation | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jurek Leonhardt | 1 | 0 | 0.34 |
Koustav Rudra | 2 | 5 | 2.62 |
Megha Khosla | 3 | 18 | 6.01 |
Abhijit Anand | 4 | 0 | 0.68 |
Avishek Anand | 5 | 0 | 1.01 |