Number of the records: 1
Using Paraphrasers to Detect Duplicities in Ontologies
- 1.
SYSNO ASEP 0580726 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Using Paraphrasers to Detect Duplicities in Ontologies Author(s) Korel, L. (CZ)
Behr, A. S. (DE)
Kockmann, N. (DE)
Holeňa, Martin (UIVT-O) SAI, RIDSource Title Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2. - Setubal : SciTePress, 2023 / Aveiro D. ; Dietz J. ; Poggi A. ; Bernardino J. - ISSN 2184-3228 - ISBN 978-989-758-671-2 Pages s. 40-49 Number of pages 10 s. Publication form Online - E Action KEOD 2023: Conference on Knowledge Engineering and Ontology Development /15./ Event date 13.11.2023 - 15.11.2023 VEvent location Rome / hybrid Country IT - Italy Event type WRD Language eng - English Country PT - Portugal Keywords Classifiers ; Duplicity Detection ; Ontologies ; Paraphrasers ; Representation Learning ; Semantic Similarity OECD category Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) Research Infrastructure ELIXIR CZ III - 90255 - Ústav organické chemie a biochemie AV ČR, v. v. i.
e-INFRA CZ II - 90254 - CESNET, zájmové sdružení právnických osobInstitutional support UIVT-O - RVO:67985807 EID SCOPUS 85179547769 DOI 10.5220/0012164500003598 Annotation This paper contains a machine-learning-based approach to detect duplicities in ontologies. Ontologies are formal specifications of shared conceptualizations of application domains. Merging and enhancing ontologies may cause the introduction of duplicities into them. The approach to duplicities proposed in this work presents a solution that does not need manual corrections by domain experts. Source texts consist of short textual descriptions from considered ontologies, which have been extracted and automatically paraphrased to receive pairs of sentences with the same or a very close meaning. The sentences in the received dataset have been embedded into Euclidean vector space. The classification task was to determine whether a given pair of sentence embeddings is semantically equivalent or different. The results have been tested using test sets generated by paraphrases as well as on a small real-world ontology. We also compared solutions by the most similar existing approach, based on GloVe and WordNet, with solutions by our approach. According to all considered metrics, our approach yielded better results than the compared approach. From the results of both experiments, the most suitable for the detection of duplicities in ontologies is the combination of BERT with support vector machines. Finally, we performed an ablation study to validate whether all paraphrasers used to create the training set for the classification were essential. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2024 Electronic address https://doi.org/10.5220/0012164500003598
Number of the records: 1