Exploring Prompt Generation Utilizing Graph Search Algorithms for Ontology Matching

Kurzanzeige
dc.contributor.authorSampels, Julian
dc.contributor.authorEfeoglu, Sefika
dc.contributor.authorSchimmler, Sonja
dc.contributor.editorSalatino, Angelo
dc.contributor.editorAlam, Mehwish
dc.contributor.editorOngenae, Femke
dc.contributor.editorVahdati, Sahar
dc.contributor.editorGentile, Anna-Lisa
dc.contributor.editorPellegrini, Tassilo
dc.contributor.editorJiang, Shufan
dc.date.accessioned2025-03-31T13:51:14Z
dc.date.available2025-03-31T13:51:14Z
dc.date.issued2024
dc.description.abstractThe interoperability of domain ontologies, developed by domain experts, necessitates their alignment before attempting to match them. Within these ontologies, defined concepts often encounter an ambiguity problem stemming from the use of natural language. This interoperability issue raises the underlying ontology matching (OM) challenge. OM might be defined as the identification of correspondences or relationships between two or more entities, such as classes or properties among two or more ontologies. Rule-based ontology matching approaches, e.g., LogMap and AML have not outperformed machine learning based matchers on the Ontology Alignment Evaluation Initiative (OAEI) benchmark datasets, especially on the OAEI Conference track since 2020. Supervised machine or deep learning approaches produce the best results but require labeled training datasets. In the era of Large Language Models (LLMs), robust zero-shot prompting of LLMs can also return convincing responses. While prompt generation requires prompt template engineering by domain experts, contextual information about the concepts to be aligned can be retrieved by leveraging graph search algorithms. In this work, we explore how graph search algorithms, namely (i) Random Walk and (ii) Tree Traversal can be utilized to retrieve the contextual information to be incorporated into prompt templates. Through these algorithms, our approach refrains from considering all triples connected with a concept to be aligned in its contextual information creation. Our experiments show that including the retrieved contextual information in prompt templates improves the matcher’s performance. Additionally, our approach outperforms previous works leveraging zero-shot prompting.
dc.identifier.citationSampels, J., Efeoglu, S., & Schimmler, S. (2024). Exploring Prompt Generation Utilizing Graph Search Algorithms for Ontology Matching. In A. Salatino, M. Alam, F. Ongenae, S. Vahdati, A.-L. Gentile, T. Pellegrini, & S. Jiang (Eds.), Proceedings of the 20th International Conference on Semantic Systems, 17–19 September 2024, Amsterdam, The Netherlands (pp. 2–19). IOS Press. https://doi.org/10.3233/SSW240003
dc.identifier.doi10.3233/SSW240003
dc.identifier.isbn978-1-64368-537-3
dc.identifier.urihttps://www.weizenbaum-library.de/handle/id/866
dc.language.isoeng
dc.publisherIOS Press
dc.rightsopen access
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectGraph Search
dc.subjectPrompt Generation
dc.subjectOntology Matching
dc.subjectZero-Shot Prompting
dc.titleExploring Prompt Generation Utilizing Graph Search Algorithms for Ontology Matching
dc.typeConferencePaper
dc.type.statuspublishedVersion
dcmi.typeText
dcterms.bibliographicCitation.urlhttps://doi.org/10.3233/SSW240003
local.researchgroupDigitalisierung und Öffnung der Wissenschaft
local.researchtopicOrganisation von Wissen
Dateien
Originalbündel
Gerade angezeigt 1 - 1 von 1
Vorschaubild
Name:
Schimmler_ea_Exploring-Prompt-Gen.pdf
Größe:
421.56 KB
Format:
Adobe Portable Document Format
Beschreibung:
Herunterladen
Sammlungen
Organisation von Wissen. Zwischen Offenheit und Exklusivität
Conference Papers