%0 Conference Paper %1 10.1145/3485447.3511955 %A Leonhardt, Jurek %A Rudra, Koustav %A Khosla, Megha %A Anand, Abhijit %A Anand, Avishek %B Proceedings of the ACM Web Conference 2022 %C New York, NY, USA %D 2022 %I Association for Computing Machinery %K efficiency myown neural-ranking %P 266–276 %R 10.1145/3485447.3511955 %T Efficient Neural Ranking Using Forward Indexes %U https://doi.org/10.1145/3485447.3511955 %X 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. %@ 9781450390965

@inproceedings{10.1145/3485447.3511955, 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.}, added-at = {2022-11-08T08:50:44.000+0100}, address = {New York, NY, USA}, author = {Leonhardt, Jurek and Rudra, Koustav and Khosla, Megha and Anand, Abhijit and Anand, Avishek}, biburl = {https://www.bibsonomy.org/bibtex/2dd66fdd71a1c0beef5a06b311ab31151/leonhardt}, booktitle = {Proceedings of the ACM Web Conference 2022}, doi = {10.1145/3485447.3511955}, interhash = {9a1c4af4b6c3ba3e3b29a9b451a54188}, intrahash = {dd66fdd71a1c0beef5a06b311ab31151}, isbn = {9781450390965}, keywords = {efficiency myown neural-ranking}, location = {Virtual Event, Lyon, France}, numpages = {11}, pages = {266–276}, publisher = {Association for Computing Machinery}, series = {WWW '22}, timestamp = {2022-11-08T08:50:44.000+0100}, title = {Efficient Neural Ranking Using Forward Indexes}, url = {https://doi.org/10.1145/3485447.3511955}, year = 2022 }