DaSeLab at LLMs4OL 2024 Task A: Towards Term Typing in Ontology Learning
Open Conference Proceedings · 02.10.2024 · 4 · 77-84
DOI: 10.52825/ocp.v4i.2489 ↗Kurz gefasst
Fachartikel in der Zeitschrift Open Conference Proceedings, online erschienen am 02.10.2024. Verfasst von Adrita Barua und 2 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 8 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.
Abstract (Originalsprache)
The report presents the evaluation results of our approach in the LLM4OL Challenge, where we fine-tuned GPT-3.5 for Task A (Term Typing) across three different datasets. Our approach demonstrated consistent and robust performance during few- shot testing, achieving top rankings in several datasets and sub-datasets, proving the potential of fine-tuning LLMs for ontology creation tasks.
Förderung
- National Science Foundation
Zitieren
APA
Barua, A., Norouzi, S. S., & Hitzler, P. (2024). DaSeLab at LLMs4OL 2024 Task A: Towards Term Typing in Ontology Learning. Open Conference Proceedings, 4, 77-84. https://doi.org/10.52825/ocp.v4i.2489
Vancouver
Barua A, Norouzi SS, Hitzler P. DaSeLab at LLMs4OL 2024 Task A: Towards Term Typing in Ontology Learning. Open Conference Proceedings. 2024;4:77-84. doi:10.52825/ocp.v4i.2489
BibTeX
@article{Barua2024,
author = {Barua, Adrita and Norouzi, Sanaz Saki and Hitzler, Pascal},
title = {DaSeLab at LLMs4OL 2024 Task A: Towards Term Typing in Ontology Learning},
journal = {Open Conference Proceedings},
year = {2024},
volume = {4},
pages = {77--84},
doi = {10.52825/ocp.v4i.2489}
}
EUVIMED