Loading [MathJax]/extensions/tex2jax.js

Leveraging GPT Models For Semantic Table Annotation

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autorschaft

  • Jean Petit Bikim
  • Carick Atezong
  • Azanzi Jiomekong
  • Allard Oelen
  • Gollam Rabby
  • Sören Auer

Organisationseinheiten

Externe Organisationen

  • Technische Informationsbibliothek (TIB) Leibniz-Informationszentrum Technik und Naturwissenschaften und Universitätsbibliothek
  • University of Yaounde I

Details

OriginalspracheEnglisch
Titel des SammelwerksSemantic Web Challenge on Tabular Data to Knowledge Graph Matching 2024
UntertitelProceedings of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching
Seiten43-53
Seitenumfang11
PublikationsstatusVeröffentlicht - 3 Jan. 2025
Veranstaltung2024 Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, SemTab 2024 - Baltimore, USA / Vereinigte Staaten
Dauer: 13 Nov. 202413 Nov. 2024

Publikationsreihe

NameCEUR workshop proceedings
Herausgeber (Verlag)CEUR-WS
Band3889
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.

ASJC Scopus Sachgebiete

Zitieren

Leveraging GPT Models For Semantic Table Annotation. / Bikim, Jean Petit; Atezong, Carick; Jiomekong, Azanzi et al.
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. S. 43-53 (CEUR workshop proceedings; Band 3889).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Bikim, JP, Atezong, C, Jiomekong, A, Oelen, A, Rabby, G, D’Souza, J & Auer, S 2025, Leveraging GPT Models For Semantic Table Annotation. in Semantic Web Challenge on Tabular Data to Knowledge Graph Matching 2024: Proceedings of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching. CEUR workshop proceedings, Bd. 3889, S. 43-53, 2024 Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, SemTab 2024, Baltimore, USA / Vereinigte Staaten, 13 Nov. 2024. <https://ceur-ws.org/Vol-3889/paper3.pdf>
Bikim, J. P., Atezong, C., Jiomekong, A., Oelen, A., Rabby, G., D’Souza, J., & Auer, S. (2025). Leveraging GPT Models For Semantic Table Annotation. In Semantic Web Challenge on Tabular Data to Knowledge Graph Matching 2024: Proceedings of the Semantic Web Challenge on Tabular Data to Knowledge Graph Matching (S. 43-53). (CEUR workshop proceedings; Band 3889). https://ceur-ws.org/Vol-3889/paper3.pdf
Bikim JP, Atezong C, Jiomekong A, Oelen A, Rabby G, D’Souza J et al. Leveraging GPT Models For Semantic Table Annotation. in 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. S. 43-53. (CEUR workshop proceedings).
Bikim, Jean Petit ; Atezong, Carick ; Jiomekong, Azanzi et al. / Leveraging GPT Models For Semantic Table Annotation. 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. S. 43-53 (CEUR workshop proceedings).
Download
@inproceedings{e4c30472363b4b3c99659490cdfaad4e,
title = "Leveraging GPT Models For Semantic Table Annotation",
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",
author = "Bikim, {Jean Petit} and Carick Atezong and Azanzi Jiomekong and Allard Oelen and Gollam Rabby and Jennifer D{\textquoteright}Souza and S{\"o}ren Auer",
note = "Publisher Copyright: {\textcopyright} 2024 Copyright for this paper by its authors.; 2024 Semantic Web Challenge on Tabular Data to Knowledge Graph Matching, SemTab 2024 ; Conference date: 13-11-2024 Through 13-11-2024",
year = "2025",
month = jan,
day = "3",
language = "English",
series = "CEUR workshop proceedings",
publisher = "CEUR-WS",
pages = "43--53",
booktitle = "Semantic Web Challenge on Tabular Data to Knowledge Graph Matching 2024",

}

Download

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 -

Von denselben Autoren