Fine-tuning SBERT for Semantic Research Title Classification in Trilingual University Repository
Kurdistan Journal of Applied Research · 03.09.2025 · 10 (2) · 119-135
DOI: 10.24017/science.2025.2.9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Kurdistan Journal of Applied Research, online erschienen am 03.09.2025. Verfasst von Havan Wahid Rashid und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Recommendation systems are essential for automatically surfacing relevant content from large datasets, reducing search time, and facilitating discovery. In academia, content-based recommendation systems are beneficial when only brief titles are available and multilingual text is standard. Universities in the Kurdistan Regional Government currently lack a centralized research repository, with records scattered across different institutions and often manually maintained. This makes it difficult for students and faculty to find related topics, potential supervisors, or cross-disciplinary connections. This paper presents a trilingual (English, Arabic, and Kurdish) recommendation system for academic research titles. Three key contributions are made: (1) the creation of the first integrated dataset of 4,257 research titles from Sulaimani Polytechnic University publicly available; (2) the development of a web-based platform for semantic search and title-level recommendations to support research discovery and student–supervisor matching; and (3) an evaluation between Sentence-BERT models—all-MiniLM-L6-v2 and paraphrase-multilingual-MiniLM-L12-v2—before and after fine-tuning with a domain-specific taxonomy and cosine embedding loss. Performance is assessed using Precision@5, Mean Reciprocal Rank, and NDCG@5 with expert-annotated relevance judgments for 20 query titles. Fine-tuning resulted in performance improvements, with paraphrase-multilingual-MiniLM-L12-v2 achieving Precision@5 of 0.94 and NDCG@5 of 0.991. The English-only model also showed improvements, Precision@5: 0.79→0.82; NDCG@5: 0.885→0.922.
Zitieren
APA
Rashid, H. W., & Ahmed, S. H. (2025). Fine-tuning SBERT for Semantic Research Title Classification in Trilingual University Repository. Kurdistan Journal of Applied Research, 10(2), 119-135. https://doi.org/10.24017/science.2025.2.9
Vancouver
Rashid HW, Ahmed SH. Fine-tuning SBERT for Semantic Research Title Classification in Trilingual University Repository. Kurdistan Journal of Applied Research. 2025;10(2):119-135. doi:10.24017/science.2025.2.9
BibTeX
@article{Rashid2025,
author = {Rashid, Havan Wahid and Ahmed, Sarkar Hasan},
title = {Fine-tuning SBERT for Semantic Research Title Classification in Trilingual University Repository},
journal = {Kurdistan Journal of Applied Research},
year = {2025},
volume = {10},
number = {2},
pages = {119--135},
doi = {10.24017/science.2025.2.9}
}
EUVIMED