2000 character limit reached
Embedding Ontologies via Incorporating Extensional and Intensional Knowledge
Published 20 Jan 2024 in cs.AI and cs.CL | (2402.01677v5)
Abstract: Ontologies contain rich knowledge within domain, which can be divided into two categories, namely extensional knowledge and intensional knowledge. Extensional knowledge provides information about the concrete instances that belong to specific concepts in the ontology, while intensional knowledge details inherent properties, characteristics, and semantic associations among concepts. However, existing ontology embedding approaches fail to take both extensional knowledge and intensional knowledge into fine consideration simultaneously. In this paper, we propose a novel ontology embedding approach named EIKE (Extensional and Intensional Knowledge Embedding) by representing ontologies in two spaces, called extensional space and intensional space. EIKE presents a unified framework for embedding instances, concepts and their relations in an ontology, applying a geometry-based method to model extensional knowledge and a pretrained LLM to model intensional knowledge, which can capture both structure information and textual information. Experimental results show that EIKE significantly outperforms state-of-the-art methods in three datasets for both triple classification and link prediction, indicating that EIKE provides a more comprehensive and representative perspective of the domain.
- Semantic search using modular ontology learning and case-based reasoning. In Proceedings of the 2010 EDBT/ICDT Workshops, pages 1–12, 2010.
- Translating embeddings for modeling multi-relational data. Advances in neural information processing systems, 26, 2013.
- Owl2vec*: Embedding of owl ontologies. Machine Learning, 110(7):1813–1845, 2021.
- Knowledge is flat: A seq2seq generative framework for various knowledge graph completion, 2022.
- Mathieu d’Aquin. Tabiic: Taxonomy building through iterative and interactive clustering. arXiv preprint arXiv:2312.05866, 2023.
- Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805, 2018.
- Cosine-based embedding for completing schematic knowledge. In Natural Language Processing and Chinese Computing: 8th CCF International Conference, NLPCC 2019, Dunhuang, China, October 9–14, 2019, Proceedings, Part I 8, pages 249–261. Springer, 2019.
- Relational message passing for fully inductive knowledge graph completion. In 2023 IEEE 39th International Conference on Data Engineering (ICDE), pages 1221–1233. IEEE, 2023.
- Universal representation learning of knowledge bases by jointly embedding instances and ontological concepts. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 1709–1719, 2019.
- Dual-geometric space embedding model for two-view knowledge graphs. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 676–686, 2022.
- Knowledge graph embedding via dynamic mapping matrix. In Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (volume 1: Long papers), pages 687–696, 2015.
- Ontology repositories and semantic artefact catalogues with the ontoportal technology. In International Semantic Web Conference, pages 38–58. Springer, 2023.
- Ontology-based information retrieval model for the semantic web. In 2005 IEEE International Conference on e-Technology, e-Commerce and e-Service, pages 152–155. IEEE, 2005.
- El embeddings: Geometric construction of models for the description logic el++. arXiv preprint arXiv:1902.10499, 2019.
- Learning entity and relation embeddings for knowledge graph completion. In Proceedings of the AAAI conference on artificial intelligence, volume 29, 2015.
- Differentiating concepts and instances for knowledge graph embedding. arXiv preprint arXiv:1811.04588, 2018.
- George A Miller. Wordnet: a lexical database for english. Communications of the ACM, 38(11):39–41, 1995.
- The use of ontologies for effective knowledge modelling and information retrieval. Applied Computing and Informatics, 14(2):116–126, 2018.
- An introduction to description logics. Description logic handbook, 1:40, 2003.
- A three-way model for collective learning on multi-relational data. In Icml, volume 11, pages 3104482–3104584, 2011.
- Holographic embeddings of knowledge graphs. In Proceedings of the AAAI conference on artificial intelligence, volume 30, 2016.
- Bioportal: ontologies and integrated data resources at the click of a mouse. Nucleic acids research, 37(suppl_2):W170–W173, 2009.
- Learning the concept embeddings of ontology. In Advanced Data Mining and Applications: 16th International Conference, ADMA 2020, Foshan, China, November 12–14, 2020, Proceedings 16, pages 127–134. Springer, 2020.
- Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:1908.10084, 2019.
- Onto2vec: joint vector-based representation of biological entities and their ontology-based annotations. Bioinformatics, 34(13):i52–i60, 2018.
- Opa2vec: combining formal and informal content of biomedical ontologies to improve similarity-based prediction. Bioinformatics, 35(12):2133–2140, 2019.
- Yago: a core of semantic knowledge. In Proceedings of the 16th international conference on World Wide Web, pages 697–706, 2007.
- Complex embeddings for simple link prediction. In International conference on machine learning, pages 2071–2080. PMLR, 2016.
- Knowledge graph embedding by translating on hyperplanes. In Proceedings of the AAAI conference on artificial intelligence, volume 28, 2014.
- Semantic technology. Springer, 2020.
- Kepler: A unified model for knowledge embedding and pre-trained language representation. Transactions of the Association for Computational Linguistics, 9:176–194, 2021.
- From discrimination to generation: Knowledge graph completion with generative transformer. In Companion Proceedings of the Web Conference 2022, WWW ’22. ACM, April 2022.
- Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:1412.6575, 2014.
- Kg-bert: Bert for knowledge graph completion. arXiv preprint arXiv:1909.03193, 2019.
- Exploring large language models for knowledge graph completion, 2023.
- Transfg: A fine-grained model for knowledge graph embedding. In Web Information Systems and Applications: 16th International Conference, WISA 2019, Qingdao, China, September 20-22, 2019, Proceedings 16, pages 455–466. Springer, 2019.
- Geometry-based anisotropy representation learning of concepts for knowledge graph embedding. Applied Intelligence, pages 1–22, 2023.
- Pretrain-kge: learning knowledge representation from pretrained language models. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 259–266, 2020.
- Inductive relation inference of knowledge graph enhanced by ontology information. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 6491–6502, 2023.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.