Building Lightweight Semantic Search Engines

Michael Rovatsos, Rosa Filgueira

Research output: Chapter in Book/Report/Conference proceedingConference 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 languageEnglish
Title of host publicationProceedings of the 19th IEEE Conference on eScience (eScience 2023)
Number of pages10
ISBN (Electronic)9798350322231
ISBN (Print)9798350322248
Publication statusPublished - 25 Sept 2023
Event19th IEEE International Conference on e-Science - Limassol, Cyprus
Duration: 9 Oct 202313 Oct 2023
Conference number: 19

Publication series

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


Conference19th IEEE International Conference on e-Science
Abbreviated titleeScience 2023
Internet address

Keywords / Materials (for Non-textual outputs)

  • Semantic search
  • natural language technologies
  • knowledge graphs
  • neural information retrieval


Dive into the research topics of 'Building Lightweight Semantic Search Engines'. Together they form a unique fingerprint.

Cite this