Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1386510,
author = {Rygl, Jan and Pomikálek, Jan and Řehůřek, Radim and Růžička, Michal and Novotný, Vít and Sojka, Petr},
address = {Vancouver, Canada},
booktitle = {Proceedings of the 2nd Workshop on Representation Learning for NLP, RepL4NLP 2017 c/o ACL 2017},
doi = {http://dx.doi.org/10.18653/v1/W17-2611},
keywords = {full-text search; similarity search; vector space; embeddings},
howpublished = {elektronická verze "online"},
language = {eng},
location = {Vancouver, Canada},
isbn = {978-1-945626-62-3},
pages = {81-90},
publisher = {Association for Computational Linguistics, ACL},
title = {Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines},
url = {https://arxiv.org/abs/1706.00957},
year = {2017}
}
TY - JOUR
ID - 1386510
AU - Rygl, Jan - Pomikálek, Jan - Řehůřek, Radim - Růžička, Michal - Novotný, Vít - Sojka, Petr
PY - 2017
TI - Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines
PB - Association for Computational Linguistics, ACL
CY - Vancouver, Canada
SN - 9781945626623
KW - full-text search
KW - similarity search
KW - vector space
KW - embeddings
UR - https://arxiv.org/abs/1706.00957
L2 - https://doi.org/10.18653/v1/W17-2611
N2 - Vector representations and vector space modeling (VSM) play a central role in modern machine learning. We propose a novel approach to ‘vector similarity searching’ over dense semantic representations of words and documents that can be deployed on top of traditional inverted-index-based fulltext engines, taking advantage of their robustness, stability, scalability and ubiquity. We show that this approach allows the indexing and querying of dense vectors in text domains. This opens up exciting avenues for major efficiency gains, along with simpler deployment, scaling and monitoring. The end result is a fast and scalable vector database with a tunable trade-off between vector search performance and quality, backed by a standard fulltext engine such as Elasticsearch. We empirically demonstrate its querying performance and quality by applying this solution to the task of semantic searching over a dense vector representation of the entire English Wikipedia.
ER -
RYGL, Jan, Jan POMIKÁLEK, Radim ŘEHŮŘEK, Michal RŮŽIČKA, Vít NOVOTNÝ and Petr SOJKA. Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines. Online. In \textit{Proceedings of the 2nd Workshop on Representation Learning for NLP, RepL4NLP 2017 c/o ACL 2017}. Vancouver, Canada: Association for Computational Linguistics, ACL, 2017, p.~81-90. ISBN~978-1-945626-62-3. Available from: https://dx.doi.org/10.18653/v1/W17-2611.
|
