VectorSearch: Enhancing Document Retrieval with Semantic Embeddings and Optimized Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Monir, Solmaz Seyed, Lau, Irene, Yang, Shubing, Zhao, Dongfang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917787363966976
author Monir, Solmaz Seyed
Lau, Irene
Yang, Shubing
Zhao, Dongfang
author_facet Monir, Solmaz Seyed
Lau, Irene
Yang, Shubing
Zhao, Dongfang
contents Traditional retrieval methods have been essential for assessing document similarity but struggle with capturing semantic nuances. Despite advancements in latent semantic analysis (LSA) and deep learning, achieving comprehensive semantic understanding and accurate retrieval remains challenging due to high dimensionality and semantic gaps. The above challenges call for new techniques to effectively reduce the dimensions and close the semantic gaps. To this end, we propose VectorSearch, which leverages advanced algorithms, embeddings, and indexing techniques for refined retrieval. By utilizing innovative multi-vector search operations and encoding searches with advanced language models, our approach significantly improves retrieval accuracy. Experiments on real-world datasets show that VectorSearch outperforms baseline metrics, demonstrating its efficacy for large-scale retrieval tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17383
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VectorSearch: Enhancing Document Retrieval with Semantic Embeddings and Optimized Search
Monir, Solmaz Seyed
Lau, Irene
Yang, Shubing
Zhao, Dongfang
Information Retrieval
Artificial Intelligence
Databases
Machine Learning
Performance
Traditional retrieval methods have been essential for assessing document similarity but struggle with capturing semantic nuances. Despite advancements in latent semantic analysis (LSA) and deep learning, achieving comprehensive semantic understanding and accurate retrieval remains challenging due to high dimensionality and semantic gaps. The above challenges call for new techniques to effectively reduce the dimensions and close the semantic gaps. To this end, we propose VectorSearch, which leverages advanced algorithms, embeddings, and indexing techniques for refined retrieval. By utilizing innovative multi-vector search operations and encoding searches with advanced language models, our approach significantly improves retrieval accuracy. Experiments on real-world datasets show that VectorSearch outperforms baseline metrics, demonstrating its efficacy for large-scale retrieval tasks.
title VectorSearch: Enhancing Document Retrieval with Semantic Embeddings and Optimized Search
topic Information Retrieval
Artificial Intelligence
Databases
Machine Learning
Performance
url https://arxiv.org/abs/2409.17383