Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1392125,
author = {Růžička, Michal and Novotný, Vít and Sojka, Petr and Pomikálek, Jan and Řehůřek, Radim},
address = {Vienna, Austria},
booktitle = {CEUR Workshop Proceedings, Vol. 1923},
keywords = {vector space modelling; semantic vectors encodings; inverted-index; systems performance; document representations; Latent Semantic Analysis; doc2vec; GloVe; Elasticsearch; evaluation; performance optimization},
howpublished = {elektronická verze "online"},
language = {eng},
location = {Vienna, Austria},
pages = {1-12},
publisher = {Neuveden},
title = {Flexible Similarity Search of Semantic Vectors Using Fulltext Search Engines},
url = {https://usc-isi-i2.github.io/ISWC17workshop/},
year = {2017}
}
TY - JOUR
ID - 1392125
AU - Růžička, Michal - Novotný, Vít - Sojka, Petr - Pomikálek, Jan - Řehůřek, Radim
PY - 2017
TI - Flexible Similarity Search of Semantic Vectors Using Fulltext Search Engines
PB - Neuveden
CY - Vienna, Austria
KW - vector space modelling
KW - semantic vectors encodings
KW - inverted-index
KW - systems performance
KW - document representations
KW - Latent Semantic Analysis
KW - doc2vec
KW - GloVe
KW - Elasticsearch
KW - evaluation
KW - performance optimization
UR - https://usc-isi-i2.github.io/ISWC17workshop/
N2 - Vector representations and vector space modeling (VSM) play a central role in modern machine learning. In our recent research we proposed a novel approach to ‘vector similarity searching’ over dense semantic vector representations. This approach can be deployed on top of traditional inverted-index-based fulltext engines, taking advantage of their robustness, stability, scalability and ubiquity. In this paper we validate our method using varied datasets ranging from text representations and embeddings (LSA, doc2vec, GloVe) to SIFT descriptors of image data. We show how our approach handles the indexing and querying in these domains, building 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.
ER -
RŮŽIČKA, Michal, Vít NOVOTNÝ, Petr SOJKA, Jan POMIKÁLEK and Radim ŘEHŮŘEK. Flexible Similarity Search of Semantic Vectors Using Fulltext Search Engines. Online. In \textit{CEUR Workshop Proceedings, Vol. 1923}. Vienna, Austria: Neuveden, 2017, p.~1-12. ISSN~1613-0073.
|
