City Research Online

Abstract

This paper investigates the use of a Large Language Model (LLM) to match tabular data with knowledge graphs. The system participated in the STI vs. LLMs 2024 SemTab Track, which prompts a model to perform the cell entity annotation (CEA) task. The study covers the processes from data cleaning and matching to its execution in the cloud, while relying on a Lookup API to generate a list of candidates. This project not only contributes to the understanding of the applications of Large Language Models in tabular data annotations but also lays the groundwork for future research in the field.

Publication Type:	Conference or Workshop Item (Paper)
Publisher Keywords:	Tabular Data Annotation, Knowledge Graphs, Large Language Model, SemTab Challenge, Entity Matching
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science
Departments:	School of Science & Technology School of Science & Technology > Computer Science
SWORD Depositor:	Symplectic Administrator

Export

Downloads