Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F03892620%3A_____%2F17%3AN0000005" target="_blank" >RIV/03892620:_____/17:N0000005 - isvavai.cz</a>
Alternative codes found
RIV/00216224:14330/17:00094366
Result on the web
<a href="http://www.aclweb.org/anthology/W17-2611" target="_blank" >http://www.aclweb.org/anthology/W17-2611</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/W17-2611" target="_blank" >10.18653/v1/W17-2611</a>

Result language
angličtina
Original language name
Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines
Original language description
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.
Czech name
—
Czech description
—

Project
<a href="/en/project/TD03000295" target="_blank" >TD03000295: Intelligent software for semantic text search</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings of the 2nd Workshop on Representation Learning for NLP
ISBN
978-1-945626-62-3
ISSN
—
e-ISSN
—
Number of pages
10
Pages from-to
81-90
Publisher name
Association for Computational Linguistics
Place of publication
Vancouver, Canada
Event location
Vancouver, Canada
Event date
Jan 1, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)