Melola Discovery

← Melola Discovery

Jurnal SINTA 2

Fine-tuning NER for Triplet Extraction in Medical Knowledge Graph Construction

Journal of ICT Research and Applications (JICTRA) · Vol. 19 No. 2 (2025) · pp. 105–119

DOI
10.5614/itbj.ict.res.appl.2025.19.2.1
ISSN
2338-5499, 2337-5787
Published
2025-12-18
Publisher
DRI - ITB
Language
eng

Abstract

This study presents a new approach for constructing a medical knowledge graph using Named Entity Recognition (NER) to identify entities such as diseases, drugs, or medical procedures, alongside part-of-speech (POS) tagging and dependency parsing to determine words that function as verbs and roots. These extracted words are then used as relations between entities, forming triplets in the format (entity, relation, entity). While the knowledge graph provides a structured representation of medical information, the evaluation primarily reflects the performance of the underlying NLP pipeline (NER, POS tagging, and dependency parsing) used to generate the triplets. Quantitative evaluation was performed using metrics such as precision, recall, and F1-score to assess the accuracy and completeness of entity and relation extraction. The qualitative evaluation involved medical domain experts to assess the relevance and validity of the relationships derived. The results indicate that fine-tuning a pre-trained model for NER and leveraging a pre-trained model for POS tagging and dependency parsing can effectively generate accurate triplets for constructing a medical knowledge graph. This approach demonstrated strong performance, achieving high evaluation scores in both quantitative and qualitative evaluations.

Keywords

Collaboration network of the authors

15 authors · 25 co-authorship links · 3 across different organisations

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Bandung Institute of Technology
  • Indonesia University of Education
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Dwi Hendratmo WidyantoroBandung Institute of Technology4
Bambang Riyanto TrilaksonoBandung Institute of Technology3
E. Aminudin AzizIndonesia University of Education3
Muhammad Haris MaulanaBandung Institute of Technology1
Jan Wira Gotama PutraBandung Institute of Technology1
Ghoziyah Haitan RachmanBandung Institute of Technology1
Carmadi MachbubBandung Institute of Technology1
Wahyudi WahyudiBandung Institute of Technology1
Ary Setijadi PrihatmantoBandung Institute of Technology1
Benhard SitohangBandung Institute of Technology1
Gusti Ayu Putri SaptawatiBandung Institute of Technology1
Nasy`an Taufiq Al GhifariBandung Institute of Technology1
Bariza HaqiBandung Institute of Technology1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://journals.itb.ac.id/index.php/jictra/oai, first harvested 26 Okt 2026, last seen 26 Okt 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Fine-tuning NER for Triplet Extraction in Medical Knowledge Graph Construction</dc:title>
	<dc:creator>Reinhart, Richard</dc:creator>
	<dc:creator>Khodra, Masayu Leylia</dc:creator>
	<dc:subject xml:lang="en-US">dependency parsing</dc:subject>
	<dc:subject xml:lang="en-US">medical knowledge graph</dc:subject>
	<dc:subject xml:lang="en-US">named entity recognition</dc:subject>
	<dc:subject xml:lang="en-US">part-of-speech tagging</dc:subject>
	<dc:subject xml:lang="en-US">triplets</dc:subject>
	<dc:description xml:lang="en-US">This study presents a new approach for constructing a medical knowledge graph using Named Entity Recognition (NER) to identify entities such as diseases, drugs, or medical procedures, alongside part-of-speech (POS) tagging and dependency parsing to determine words that function as verbs and roots. These extracted words are then used as relations between entities, forming triplets in the format (entity, relation, entity). While the knowledge graph provides a structured representation of medical information, the evaluation primarily reflects the performance of the underlying NLP pipeline (NER, POS tagging, and dependency parsing) used to generate the triplets. Quantitative evaluation was performed using metrics such as precision, recall, and F1-score to assess the accuracy and completeness of entity and relation extraction. The qualitative evaluation involved medical domain experts to assess the relevance and validity of the relationships derived. The results indicate that fine-tuning a pre-trained model for NER and leveraging a pre-trained model for POS tagging and dependency parsing can effectively generate accurate triplets for constructing a medical knowledge graph. This approach demonstrated strong performance, achieving high evaluation scores in both quantitative and qualitative evaluations.</dc:description>
	<dc:publisher xml:lang="en-US">DRI - ITB</dc:publisher>
	<dc:date>2025-12-18</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journals.itb.ac.id/index.php/jictra/article/view/24942</dc:identifier>
	<dc:identifier>10.5614/itbj.ict.res.appl.2025.19.2.1</dc:identifier>
	<dc:source xml:lang="en-US">Journal of ICT Research and Applications; Vol. 19 No. 2 (2025); 105-119</dc:source>
	<dc:source>2338-5499</dc:source>
	<dc:source>2337-5787</dc:source>
	<dc:source>10.5614/itbj.ict.res.appl.2025.19.2</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journals.itb.ac.id/index.php/jictra/article/view/24942/7215</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 Journal of ICT Research and Applications</dc:rights>
</oai_dc:dc>