Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | WWW '22 |
| Untertitel | Proceedings of the ACM Web Conference 2022 |
| Seiten | 266-276 |
| Seitenumfang | 11 |
| ISBN (elektronisch) | 9781450390965 |
| Publikationsstatus | Veröffentlicht - 25 Apr. 2022 |
| Veranstaltung | 31st ACM World Wide Web Conference, WWW 2022 - Virtual, Online, Frankreich Dauer: 25 Apr. 2022 → 29 Apr. 2022 |
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.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Computernetzwerke und -kommunikation
- Informatik (insg.)
- Software
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
WWW '22: Proceedings of the ACM Web Conference 2022. 2022. S. 266-276.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Efficient Neural Ranking using Forward Indexes
AU - Leonhardt, Jurek
AU - Rudra, Koustav
AU - Khosla, Megha
AU - Anand, Abhijit
AU - Anand, Avishek
N1 - Funding Information: This work is supported by the National Natural Science Foundation of China (62102382,U19A2079), the USTC Research Funds of the Double First-Class Initiative (WK2100000019) and the Alibaba Innovative Research project (ATT50DHZ420003).
PY - 2022/4/25
Y1 - 2022/4/25
N2 - 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.
AB - 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.
KW - dense
KW - interpolation
KW - ranking
KW - retrieval
KW - sparse
UR - http://www.scopus.com/inward/record.url?scp=85129831935&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2110.06051
DO - 10.48550/arXiv.2110.06051
M3 - Conference contribution
AN - SCOPUS:85129831935
SP - 266
EP - 276
BT - WWW '22
T2 - 31st ACM World Wide Web Conference, WWW 2022
Y2 - 25 April 2022 through 29 April 2022
ER -