Column property annotation using large language models


Korini, Keti ; Bizer, Christian



DOI: https://doi.org/10.1007/978-3-031-78952-6_6
URL: https://link.springer.com/chapter/10.1007/978-3-03...
Additional URL: https://www.researchgate.net/publication/388437234...
Document Type: Conference or workshop publication
Year of publication: 2025
Book title: The Semantic Web: ESWC 2024 Satellite Events : Hersonissos, Crete, Greece, May 26–30, 2024, Proceedings, Part I
The title of a journal, publication series: Lecture Notes in Computer Science
Volume: 15344
Page range: 61-70
Conference title: ESWC 2024, Extended Semantic Web Conference
Location of the conference venue: Hersonissos, Crete, Greece
Date of the conference: 26.-30.05.2024
Publisher: Meroño Peñuela, Albert ; Corcho, Oscar ; Groth, Paul ; Simperl, Elena ; Tamma, Valentina ; Nuzzolese, Andrea Giovanni ; Poveda-Villalón, Maria ; Sabou, Marta ; Presutti, Valentina ; Celino, Irene ; Revenko, Artem ; Raad, Joe ; Sartini, Bruno ; Lisena, Pasquale
Place of publication: Berlin [u.a.]
Publishing house: Springer
ISBN: 978-3-031-78951-9 , 978-3-031-78952-6
ISSN: 0302-9743 , 1611-3349
Publication language: English
Institution: School of Business Informatics and Mathematics > Information Systems V: Web-based Systems (Bizer 2012-)
Subject: 004 Computer science, internet
Keywords (English): table annotation , large language models , column property annotation
Abstract: Column property annotation (CPA), also known as column relationship prediction, is the task of predicting the semantic relationship between two columns in a table given a set of candidate relationships. CPA annotations are used in downstream tasks such as data search, data integration, or knowledge graph enrichment. This paper explores the usage of generative large language models (LLMs) for the CPA task. We experiment with different zero-shot prompts for the CPA task which we evaluate using GPT-3.5, GPT-4, and the open-source model SOLAR. We find GPT-3.5 to be quite sensitive to variations of the prompt, while GPT-4 reaches a high performance independent of the variation of the prompt. We further explore the scenario where training data for the CPA task is available and can be used for selecting demonstrations or fine-tuning the model. We show that a fine-tuned GPT-3.5 model outperforms a RoBERTa model that was fine-tuned on the same data by 11% in F1. Comparing in-context learning via demonstrations and fine-tuning shows that the fine-tuned GPT-3.5 performs 9% F1 better than the same model given demonstrations. The fine-tuned GPT-3.5 model also outperforms zero-shot GPT-4 by around 2% F1 for the dataset on which is was fine-tuned, while not generalizing to tasks that require a different vocabulary.




Dieser Eintrag ist Teil der Universitätsbibliographie.




Metadata export


Citation


+ Search Authors in

BASE: Korini, Keti ; Bizer, Christian

Google Scholar: Korini, Keti ; Bizer, Christian

ORCID: Korini, Keti ; Bizer, Christian ORCID: 0000-0003-2367-0237

+ Page Views

Hits per month over past year

Detailed information



You have found an error? Please let us know about your desired correction here: E-Mail


Actions (login required)

Show item Show item