Details
| Original language | English |
|---|---|
| Title of host publication | Semantic Web Challenge on Tabular Data to Knowledge Graph Matching 2024 |
| Subtitle of host publication | Proceedings of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching |
| Pages | 43-53 |
| Number of pages | 11 |
| Publication status | Published - 3 Jan 2025 |
| Event | 2024 Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, SemTab 2024 - Baltimore, United States Duration: 13 Nov 2024 → 13 Nov 2024 |
Publication series
| Name | CEUR workshop proceedings |
|---|---|
| Publisher | CEUR-WS |
| Volume | 3889 |
| ISSN (Print) | 1613-0073 |
Abstract
This paper outlines our contribution to the Accuracy Track and the Semantic Table Interpretation (STI) & Large Language Models (LLMs) track of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching (SemTab). Our approach involves using LLMs to address the various tasks presented in the challenge. Specifically, we employed zero-shot and few-shot prompting techniques for most of the tasks, which facilitated the LLMs ability to interpret and annotate tabular data with minimal prior training. For the Column Property Annotation (CPA) task, we took a different approach by applying a set of predefined rules, tailored to the structure of each dataset. Our method achieved notable results, with an f1-score exceeding 0.92, demonstrating the effectiveness of LLMs in tackling the SemTab challenge. These results suggest that LLMs hold significant capabilities as a robust solution for semantic table annotation and knowledge graph matching, highlighting their potential to advance the field of semantic web technologies.
Keywords
- Knowledge Graph, Large Language Models, Prompt Engineering, Semantic Table Annotation, Semantic Table Interpretation, SemTab, Tabular Data
ASJC Scopus subject areas
- Computer Science(all)
- General Computer Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Semantic Web Challenge on Tabular Data to Knowledge Graph Matching 2024: Proceedings of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching. 2025. p. 43-53 (CEUR workshop proceedings; Vol. 3889).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Leveraging GPT Models For Semantic Table Annotation
AU - Bikim, Jean Petit
AU - Atezong, Carick
AU - Jiomekong, Azanzi
AU - Oelen, Allard
AU - Rabby, Gollam
AU - D’Souza, Jennifer
AU - Auer, Sören
N1 - Publisher Copyright: © 2024 Copyright for this paper by its authors.
PY - 2025/1/3
Y1 - 2025/1/3
N2 - This paper outlines our contribution to the Accuracy Track and the Semantic Table Interpretation (STI) & Large Language Models (LLMs) track of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching (SemTab). Our approach involves using LLMs to address the various tasks presented in the challenge. Specifically, we employed zero-shot and few-shot prompting techniques for most of the tasks, which facilitated the LLMs ability to interpret and annotate tabular data with minimal prior training. For the Column Property Annotation (CPA) task, we took a different approach by applying a set of predefined rules, tailored to the structure of each dataset. Our method achieved notable results, with an f1-score exceeding 0.92, demonstrating the effectiveness of LLMs in tackling the SemTab challenge. These results suggest that LLMs hold significant capabilities as a robust solution for semantic table annotation and knowledge graph matching, highlighting their potential to advance the field of semantic web technologies.
AB - This paper outlines our contribution to the Accuracy Track and the Semantic Table Interpretation (STI) & Large Language Models (LLMs) track of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching (SemTab). Our approach involves using LLMs to address the various tasks presented in the challenge. Specifically, we employed zero-shot and few-shot prompting techniques for most of the tasks, which facilitated the LLMs ability to interpret and annotate tabular data with minimal prior training. For the Column Property Annotation (CPA) task, we took a different approach by applying a set of predefined rules, tailored to the structure of each dataset. Our method achieved notable results, with an f1-score exceeding 0.92, demonstrating the effectiveness of LLMs in tackling the SemTab challenge. These results suggest that LLMs hold significant capabilities as a robust solution for semantic table annotation and knowledge graph matching, highlighting their potential to advance the field of semantic web technologies.
KW - Knowledge Graph
KW - Large Language Models
KW - Prompt Engineering
KW - Semantic Table Annotation
KW - Semantic Table Interpretation
KW - SemTab
KW - Tabular Data
UR - http://www.scopus.com/inward/record.url?scp=85214946158&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85214946158
T3 - CEUR workshop proceedings
SP - 43
EP - 53
BT - Semantic Web Challenge on Tabular Data to Knowledge Graph Matching 2024
T2 - 2024 Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, SemTab 2024
Y2 - 13 November 2024 through 13 November 2024
ER -