@inproceedings{conf/www/LeonhardtRKAA22,
  added-at = {2022-12-07T00:00:00.000+0100},
  author = {Leonhardt, Jurek and Rudra, Koustav and Khosla, Megha and Anand, Abhijit and Anand, Avishek},
  biburl = {https://www.bibsonomy.org/bibtex/2440b04709829d1a32d8641da26fd59a0/dblp},
  booktitle = {WWW},
  crossref = {conf/www/2022},
  editor = {Laforest, Frédérique and Troncy, Raphaël and Simperl, Elena and Agarwal, Deepak and Gionis, Aristides and Herman, Ivan and Médini, Lionel},
  ee = {https://doi.org/10.1145/3485447.3511955},
  interhash = {9a1c4af4b6c3ba3e3b29a9b451a54188},
  intrahash = {440b04709829d1a32d8641da26fd59a0},
  isbn = {978-1-4503-9096-5},
  keywords = {dblp},
  pages = {266-276},
  publisher = {ACM},
  timestamp = {2025-01-27T09:30:30.000+0100},
  title = {Efficient Neural Ranking using Forward Indexes.},
  url = {http://dblp.uni-trier.de/db/conf/www/www2022.html#LeonhardtRKAA22},
  year = 2022
}

@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
}