# Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines

## TL;DR

This paper introduces a method to perform efficient semantic vector similarity searches using traditional fulltext search engines like Elasticsearch, enabling scalable and robust retrieval over dense semantic representations.

## Contribution

It presents a novel approach to index and query dense semantic vectors on top of inverted-index fulltext engines, combining vector search capabilities with existing search infrastructure.

## Key findings

- Achieves fast and scalable semantic search performance.
- Demonstrates effective querying over Wikipedia's dense vector representations.
- Provides a tunable balance between search quality and performance.

## Abstract

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.