SiLi Index: Data Structure for Fast Vector Space Searching

Warning

This publication doesn't include Faculty of Medicine. It includes Faculty of Informatics. Official publication website can be found on muni.cz.
Authors

HERMAN Ondřej RYCHLÝ Pavel

Year of publication 2019
Type Article in Proceedings
Conference Proceedings of the Thirteenth Workshop on Recent Advances in Slavonic Natural Languages Processing, RASLAN 2019
MU Faculty or unit

Faculty of Informatics

Citation
Web https://nlp.fi.muni.cz/raslan/2019/paper07-herman.pdf
Keywords word embeddings; vector space; semantic similarity
Description Nearest neighbor queries in high-dimensional spaces are ex-pensive. In this article, we propose a method of building and querying astand-alone data structure, SiLi (SimilarityList) Index, which supports ap-proximating the results of k-NN queries in high-dimensional spaces, whileusing a significantly reduced amount of system memory and processortime compared to the usual brute-force search methods.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.

More info