Building Lightweight Semantic Search Engines

Michael Rovatsos; Rosa Filgueira

doi:10.1109/e-Science58273.2023.10254874

Building Lightweight Semantic Search Engines

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Despite significant advances in methods for processing large volumes of structured and unstructured data, surprisingly little attention has been devoted to developing practical methodologies that leverage state-of-the-art technologies to build domain-specific semantic search engines tailored to use cases where they could provide substantial benefits. This paper presents a methodology for developing these kinds of systems in a lightweight, modular, and flexible way with a particular focus on providing powerful search tools in domains where non-expert users encounter challenges in exploring the data repository at hand. Using an academic expertise finder tool as a case study, we demonstrate how this methodology allows us to leverage powerful off-the-shelf technology to enable the rapid, low-cost development of semantic search engines, while also affording developers with the necessary flexibility to embed user-centric design in their development in order to maximise uptake and application value.

Original language	English
Title of host publication	Proceedings of the 19th IEEE Conference on eScience (eScience 2023)
Publisher	Institute of Electrical and Electronics Engineers
Pages	1-10
Number of pages	10
ISBN (Electronic)	9798350322231
ISBN (Print)	9798350322248
DOIs	https://doi.org/10.1109/e-Science58273.2023.10254874
Publication status	Published - 25 Sept 2023
Event	19th IEEE International Conference on e-Science - Limassol, Cyprus Duration: 9 Oct 2023 → 13 Oct 2023 Conference number: 19 https://www.escience-conference.org/about/

Publication series

Name	International Conference on e-Science (e-Science)
ISSN (Print)	2325-372X
ISSN (Electronic)	2325-3703

Conference

Conference	19th IEEE International Conference on e-Science
Abbreviated title	eScience 2023
Country/Territory	Cyprus
City	Limassol
Period	9/10/23 → 13/10/23
Internet address	https://www.escience-conference.org/about/

Keywords / Materials (for Non-textual outputs)

Semantic search
natural language technologies
knowledge graphs
neural information retrieval

Access to Document

10.1109/e-Science58273.2023.10254874Licence: All Rights Reserved

Building Lightweight_ROVATSOS_DOA12072023_AFV_CC BYAccepted author manuscript, 1.68 MBLicence: Creative Commons: Attribution (CC-BY)

https://ieeexplore.ieee.org/document/10254874Licence: All Rights Reserved

Cite this

@inproceedings{8f02f488fe75426aa716b3223ebaa243,

title = "Building Lightweight Semantic Search Engines",

abstract = "Despite significant advances in methods for processing large volumes of structured and unstructured data, surprisingly little attention has been devoted to developing practical methodologies that leverage state-of-the-art technologies to build domain-specific semantic search engines tailored to use cases where they could provide substantial benefits. This paper presents a methodology for developing these kinds of systems in a lightweight, modular, and flexible way with a particular focus on providing powerful search tools in domains where non-expert users encounter challenges in exploring the data repository at hand. Using an academic expertise finder tool as a case study, we demonstrate how this methodology allows us to leverage powerful off-the-shelf technology to enable the rapid, low-cost development of semantic search engines, while also affording developers with the necessary flexibility to embed user-centric design in their development in order to maximise uptake and application value.",

keywords = "Semantic search, natural language technologies, knowledge graphs, neural information retrieval",

author = "Michael Rovatsos and Rosa Filgueira",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 19th IEEE International Conference on e-Science, eScience 2023 ; Conference date: 09-10-2023 Through 13-10-2023",

year = "2023",

month = sep,

day = "25",

doi = "10.1109/e-Science58273.2023.10254874",

language = "English",

isbn = "9798350322248",

series = "International Conference on e-Science (e-Science)",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "1--10",

booktitle = "Proceedings of the 19th IEEE Conference on eScience (eScience 2023)",

address = "United States",

url = "https://www.escience-conference.org/about/",

}

Rovatsos, M & Filgueira, R 2023, Building Lightweight Semantic Search Engines. in Proceedings of the 19th IEEE Conference on eScience (eScience 2023). International Conference on e-Science (e-Science), Institute of Electrical and Electronics Engineers, pp. 1-10, 19th IEEE International Conference on e-Science, Limassol, Cyprus, 9/10/23. https://doi.org/10.1109/e-Science58273.2023.10254874

TY - GEN

T1 - Building Lightweight Semantic Search Engines

AU - Rovatsos, Michael

AU - Filgueira, Rosa

N1 - Conference code: 19

PY - 2023/9/25

Y1 - 2023/9/25

N2 - Despite significant advances in methods for processing large volumes of structured and unstructured data, surprisingly little attention has been devoted to developing practical methodologies that leverage state-of-the-art technologies to build domain-specific semantic search engines tailored to use cases where they could provide substantial benefits. This paper presents a methodology for developing these kinds of systems in a lightweight, modular, and flexible way with a particular focus on providing powerful search tools in domains where non-expert users encounter challenges in exploring the data repository at hand. Using an academic expertise finder tool as a case study, we demonstrate how this methodology allows us to leverage powerful off-the-shelf technology to enable the rapid, low-cost development of semantic search engines, while also affording developers with the necessary flexibility to embed user-centric design in their development in order to maximise uptake and application value.

AB - Despite significant advances in methods for processing large volumes of structured and unstructured data, surprisingly little attention has been devoted to developing practical methodologies that leverage state-of-the-art technologies to build domain-specific semantic search engines tailored to use cases where they could provide substantial benefits. This paper presents a methodology for developing these kinds of systems in a lightweight, modular, and flexible way with a particular focus on providing powerful search tools in domains where non-expert users encounter challenges in exploring the data repository at hand. Using an academic expertise finder tool as a case study, we demonstrate how this methodology allows us to leverage powerful off-the-shelf technology to enable the rapid, low-cost development of semantic search engines, while also affording developers with the necessary flexibility to embed user-centric design in their development in order to maximise uptake and application value.

KW - Semantic search

KW - natural language technologies

KW - knowledge graphs

KW - neural information retrieval

U2 - 10.1109/e-Science58273.2023.10254874

DO - 10.1109/e-Science58273.2023.10254874

M3 - Conference contribution

SN - 9798350322248

T3 - International Conference on e-Science (e-Science)

SP - 1

EP - 10

BT - Proceedings of the 19th IEEE Conference on eScience (eScience 2023)

PB - Institute of Electrical and Electronics Engineers

T2 - 19th IEEE International Conference on e-Science

Y2 - 9 October 2023 through 13 October 2023

ER -

Building Lightweight Semantic Search Engines

Abstract / Description of output

Publication series

Conference

Keywords / Materials (for Non-textual outputs)

Access to Document

Fingerprint

Cite this