Implementing semantic search for textual data in web applications

Semantic search, also known as vector search, retrieves data based on their semantic similarity. It is enabled by sentence embeddings, which are high-dimension vectors that encapsulate the semantic meaning of sentences. Compared to traditional keyword search, semantic search accounts for the true in...

Full description

Bibliographic Details
Main Author: Toh, Jeremy Gen Yang
Other Authors: Andy Khong W H
Format: Final Year Project (FYP)
Language:English
Published: Nanyang Technological University 2024
Subjects:
Online Access:https://hdl.handle.net/10356/177123
_version_ 1826125679668756480
author Toh, Jeremy Gen Yang
author2 Andy Khong W H
author_facet Andy Khong W H
Toh, Jeremy Gen Yang
author_sort Toh, Jeremy Gen Yang
collection NTU
description Semantic search, also known as vector search, retrieves data based on their semantic similarity. It is enabled by sentence embeddings, which are high-dimension vectors that encapsulate the semantic meaning of sentences. Compared to traditional keyword search, semantic search accounts for the true intent of user queries which keyword search struggles to capture. This paper explores the implementation of semantic search in web applications by processing sentences using Sentence-BERT (SBERT), which is a pre-trained deep learning language model for generating meaningful, high-dimension vectors called sentence embeddings. These embeddings are then stored in PostgreSQL database with an extension, vector, which enables efficient similarity comparisons during search queries. This work details the findings from developing a vector search system, integrating it with a web application, and deploying it online.
first_indexed 2024-10-01T06:40:37Z
format Final Year Project (FYP)
id ntu-10356/177123
institution Nanyang Technological University
language English
last_indexed 2024-10-01T06:40:37Z
publishDate 2024
publisher Nanyang Technological University
record_format dspace
spelling ntu-10356/1771232024-05-31T15:43:19Z Implementing semantic search for textual data in web applications Toh, Jeremy Gen Yang Andy Khong W H School of Electrical and Electronic Engineering AndyKhong@ntu.edu.sg Computer and Information Science Engineering Semantic search Semantic search, also known as vector search, retrieves data based on their semantic similarity. It is enabled by sentence embeddings, which are high-dimension vectors that encapsulate the semantic meaning of sentences. Compared to traditional keyword search, semantic search accounts for the true intent of user queries which keyword search struggles to capture. This paper explores the implementation of semantic search in web applications by processing sentences using Sentence-BERT (SBERT), which is a pre-trained deep learning language model for generating meaningful, high-dimension vectors called sentence embeddings. These embeddings are then stored in PostgreSQL database with an extension, vector, which enables efficient similarity comparisons during search queries. This work details the findings from developing a vector search system, integrating it with a web application, and deploying it online. Bachelor's degree 2024-05-27T04:26:03Z 2024-05-27T04:26:03Z 2024 Final Year Project (FYP) Toh, J. G. Y. (2024). Implementing semantic search for textual data in web applications. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/177123 https://hdl.handle.net/10356/177123 en A3261-231 application/pdf Nanyang Technological University
spellingShingle Computer and Information Science
Engineering
Semantic search
Toh, Jeremy Gen Yang
Implementing semantic search for textual data in web applications
title Implementing semantic search for textual data in web applications
title_full Implementing semantic search for textual data in web applications
title_fullStr Implementing semantic search for textual data in web applications
title_full_unstemmed Implementing semantic search for textual data in web applications
title_short Implementing semantic search for textual data in web applications
title_sort implementing semantic search for textual data in web applications
topic Computer and Information Science
Engineering
Semantic search
url https://hdl.handle.net/10356/177123
work_keys_str_mv AT tohjeremygenyang implementingsemanticsearchfortextualdatainwebapplications