Skip to main content
SpringerLink
Log in

LLMs4OL: Large Language Models for Ontology Learning

  • Conference paper
  • First Online:
The Semantic Web – ISWC 2023 (ISWC 2023)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14265))

Included in the following conference series:

Abstract

We propose the LLMs4OL approach, which utilizes Large Language Models (LLMs) for Ontology Learning (OL). LLMs have shown significant advancements in natural language processing, demonstrating their ability to capture complex language patterns in different knowledge domains. Our LLMs4OL paradigm investigates the following hypothesis: Can LLMs effectively apply their language pattern capturing capability to OL, which involves automatically extracting and structuring knowledge from natural language text? To test this hypothesis, we conduct a comprehensive evaluation using the zero-shot prompting method. We evaluate nine different LLM model families for three main OL tasks: term typing, taxonomy discovery, and extraction of non-taxonomic relations. Additionally, the evaluations encompass diverse genres of ontological knowledge, including lexicosemantic knowledge in WordNet, geographical knowledge in GeoNames, and medical knowledge in UMLS.

The obtained empirical results show that foundational LLMs are not sufficiently suitable for ontology construction that entails a high degree of reasoning skills and domain expertise. Nevertheless, when effectively fine-tuned they just might work as suitable assistants, alleviating the knowledge acquisition bottleneck, for ontology construction.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Geonames geographical database (2023). http://www.geonames.org/

  2. Agirre, E., Ansa, O., Hovy, E., Martínez, D.: Enriching very large ontologies using the www. In: Proceedings of the First International Conference on Ontology Learning, vol. 31. pp. 25–30 (2000)

    Google Scholar 

  3. Akkalyoncu Yilmaz, Z., Wang, S., Yang, W., Zhang, H., Lin, J.: Applying BERT to document retrieval with birch. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP): System Demonstrations, pp. 19–24. Association for Computational Linguistics, Hong Kong, China (Nov 2019). https://doi.org/10.18653/v1/D19-3004, https://aclanthology.org/D19-3004

  4. Alfonseca, E., Manandhar, S.: An unsupervised method for general named entity recognition and automated concept discovery. In: Proceedings of the 1st International Conference on General WordNet, Mysore, India, pp. 34–43 (2002)

    Google Scholar 

  5. Amatriain, X.: Transformer models: an introduction and catalog. arXiv preprint arXiv:2302.07730 (2023)

  6. Asim, M.N., Wasim, M., Khan, M.U.G., Mahmood, W., Abbasi, H.M.: A survey of ontology learning techniques and applications. Database 2018, bay101 (2018)

    Google Scholar 

  7. Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: Aberer, K., et al. (eds.) ASWC/ISWC -2007. LNCS, vol. 4825, pp. 722–735. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-76298-0_52

    Chapter  Google Scholar 

  8. Bodenreider, O.: The unified medical language system (UMLS): integrating biomedical terminology. Nucleic Acids Res. 32(suppl_1), D267–D270 2004). https://doi.org/10.1093/nar/gkh061

  9. Bodenreider, O.: The unified medical language system (umls): integrating biomedical terminology. Nucleic Acids Res. 32(suppl_1), D267–D270 (2004)

    Google Scholar 

  10. Brown, T.B., et al.: Language models are few-shot learners (2020)

    Google Scholar 

  11. Chung, H.W., et al.: Scaling instruction-finetuned language models (2022)

    Google Scholar 

  12. Cui, L., Wu, Y., Liu, J., Yang, S., Zhang, Y.: Template-based named entity recognition using bart. arXiv preprint arXiv:2106.01760 (2021)

  13. Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-xl: attentive language models beyond a fixed-length context (2019)

    Google Scholar 

  14. Dalvi, F., Khan, A.R., Alam, F., Durrani, N., Xu, J., Sajjad, H.: Discovering latent concepts learned in BERT. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=POTMtpYI1xH

  15. Dettmers, T., Pasquale, M., Pontus, S., Riedel, S.: Convolutional 2d knowledge graph embeddings. In: Proceedings of the 32th AAAI Conference on Artificial Intelligence, pp. 1811–1818 (February 2018), https://arxiv.org/abs/1707.01476

  16. Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding (2019)

    Google Scholar 

  17. Dopazo, J., Carazo, J.M.: Phylogenetic reconstruction using an unsupervised growing neural network that adopts the topology of a phylogenetic tree. J. Mol. Evol. 44(2), 226–233 (1997)

    Article  Google Scholar 

  18. Gruber, T.R.: Toward principles for the design of ontologies used for knowledge sharing? Int. J. Hum Comput Stud. 43(5–6), 907–928 (1995)

    Article  Google Scholar 

  19. Gu, Y., et al.: Domain-specific language model pretraining for biomedical natural language processing. ACM Trans. Comput. Healthcare (Health) 3(1), 1–23 (2021)

    Google Scholar 

  20. Guha, R.V., Brickley, D., Macbeth, S.: Schema. org: evolution of structured data on the web. Commun. ACM 59(2), 44–51 (2016)

    Google Scholar 

  21. Hahn, U., Markó, K.G.: Joint knowledge capture for grammars and ontologies. In: Proceedings of the 1st International Conference on Knowledge Capture, pp. 68–75 (2001)

    Google Scholar 

  22. Hamp, B., Feldweg, H.: Germanet-a lexical-semantic net for german. In: Automatic Information Extraction and Building Of Lexical Semantic Resources for NLP Applications (1997)

    Google Scholar 

  23. Hearst, M.A.: Automated discovery of wordnet relations. WordNet: an electronic lexical database, vol. 2 (1998)

    Google Scholar 

  24. Hwang, C.H.: Incompletely and imprecisely speaking: using dynamic ontologies for representing and retrieving information. In: KRDB, vol. 21, pp. 14–20. Citeseer (1999)

    Google Scholar 

  25. Jiang, Z., Xu, F.F., Araki, J., Neubig, G.: How can we know what language models know? Trans. Asso. Comput. Ling. 8, 423–438 (2020). https://doi.org/10.1162/tacl_a_00324, https://aclanthology.org/2020.tacl-1.28

  26. Khan, L., Luo, F.: Ontology construction for information selection. In: 14th IEEE International Conference on Tools with Artificial Intelligence, 2002. (ICTAI 2002). Proceedings, pp. 122–127. IEEE (2002)

    Google Scholar 

  27. Khot, T., et al.: Decomposed prompting: A modular approach for solving complex tasks (2023)

    Google Scholar 

  28. Kietz, J.U., Maedche, A., Volz, R.: A method for semi-automatic ontology acquisition from a corporate intranet. In: EKAW-2000 Workshop “Ontologies and Text", Juan-Les-Pins, France (October 2000)

    Google Scholar 

  29. Kojima, T., Gu, S.S., Reid, M., Matsuo, Y., Iwasawa, Y.: Large language models are zero-shot reasoners (2023)

    Google Scholar 

  30. Konys, A.: Knowledge repository of ontology learning tools from text. Proc. Comput. Sci. 159, 1614–1628 (2019)

    Article  Google Scholar 

  31. Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)

  32. Levy, O., Seo, M., Choi, E., Zettlemoyer, L.: Zero-shot relation extraction via reading comprehension. In: Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pp. 333–342. Association for Computational Linguistics, Vancouver, Canada (Aug 2017). https://doi.org/10.18653/v1/K17-1034, https://aclanthology.org/K17-1034

  33. Lewis, M., et al.: Bart: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension (2019)

    Google Scholar 

  34. Li, X.L., Liang, P.: Prefix-tuning: optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)

  35. Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., Neubig, G.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. ACM Comput. Surv. 55(9) (2023). https://doi.org/10.1145/3560815

  36. Longpre, S., et al.: The flan collection: designing data and methods for effective instruction tuning. arXiv preprint arXiv:2301.13688 (2023)

  37. Lonsdale, D., Ding, Y., Embley, D.W., Melby, A.: Peppering knowledge sources with salt: Boosting conceptual content for ontology generation. In: Proceedings of the AAAI Workshop on Semantic Web Meets Language Resources, Edmonton, Alberta, Canada (2002)

    Google Scholar 

  38. Lourdusamy, R., Abraham, S.: A survey on methods of ontology learning from text. In: Jain, L.C., Peng, S.-L., Alhadidi, B., Pal, S. (eds.) ICICCT 2019. LAIS, vol. 9, pp. 113–123. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-38501-9_11

    Chapter  Google Scholar 

  39. Maedche, A., Staab, S.: Ontology learning for the semantic web. IEEE Intell. Syst. 16(2), 72–79 (2001)

    Article  Google Scholar 

  40. Medicomp Systems: MEDCIN (January 2023). https://medicomp.com

  41. Miller, G.A.: Wordnet: a lexical database for English. Commun. ACM 38(11), 39–41 (1995)

    Article  Google Scholar 

  42. Missikoff, M., Navigli, R., Velardi, P.: The usable ontology: an environment for building and assessing a domain ontology. In: Horrocks, I., Hendler, J. (eds.) ISWC 2002. LNCS, vol. 2342, pp. 39–53. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-48005-6_6

    Chapter  MATH  Google Scholar 

  43. Moldovan, D.I., GiRJU, R.C.: An interactive tool for the rapid development of knowledge bases. Inter. J. Artifi. Intell. Tools 10(01n02), 65–86 (2001)

    Google Scholar 

  44. National Cancer Institute, National Institutes of Health: NCI Thesaurus (September 2022). http://ncit.nci.nih.gov

  45. Noy, N.F., McGuinness, D.L., et al.: Ontology development 101: A guide to creating your first ontology (2001)

    Google Scholar 

  46. OpenAI: Chatgpt (2023). https://openai.com/chat-gpt/ (Accessed 5 May 2023)

  47. OpenAI: Gpt-4 technical report (2023)

    Google Scholar 

  48. Patel-Schneider, P.F.: Analyzing Schema.org. In: Mika, P., et al. (eds.) ISWC 2014. LNCS, vol. 8796, pp. 261–276. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-11964-9_17

    Chapter  Google Scholar 

  49. Peters, M.E., et al.: Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 2227–2237. Association for Computational Linguistics, New Orleans, Louisiana (Jun 2018). https://doi.org/10.18653/v1/N18-1202, https://aclanthology.org/N18-1202

  50. Petroni, F., et al.: How context affects language models’ factual predictions. In: Automated Knowledge Base Construction (2020). https://openreview.net/forum?id=025X0zPfn

  51. Petroni, F., et al.: Language models as knowledge bases? arXiv preprint arXiv:1909.01066 (2019)

  52. Petroni, F., et al.: Language models as knowledge bases? In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics (2019)

    Google Scholar 

  53. Rebele, T., Suchanek, F., Hoffart, J., Biega, J., Kuzey, E., Weikum, G.: YAGO: a multilingual knowledge base from wikipedia, wordnet, and geonames. In: Groth, P., et al. (eds.) ISWC 2016. LNCS, vol. 9982, pp. 177–185. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46547-0_19

    Chapter  Google Scholar 

  54. Roux, C., Proux, D., Rechenmann, F., Julliard, L.: An ontology enrichment method for a pragmatic information extraction system gathering data on genetic interactions. In: ECAI Workshop on Ontology Learning (2000)

    Google Scholar 

  55. Sajjad, H., Durrani, N., Dalvi, F., Alam, F., Khan, A.R., Xu, J.: Analyzing encoded concepts in transformer language models (2022)

    Google Scholar 

  56. Scao, T.L., et al.: Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:2211.05100 (2022)

  57. SNOMED International: US Edition of SNOMED CT (March 2023). https://www.nlm.nih.gov/healthit/snomedct/us_edition.html

  58. Speer, R., Chin, J., Havasi, C.: Conceptnet 5.5: an open multilingual graph of general knowledge. In: Proceedings of the AAAI conference on Artificial Intelligence. vol. 31 (2017)

    Google Scholar 

  59. Srivastava, A., et al.: Beyond the imitation game: quantifying and extrapolating the capabilities of language models. arXiv preprint arXiv:2206.04615 (2022)

  60. Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)

  61. Wagner, A.: Enriching a lexical semantic net with selectional preferences by means of statistical corpus analysis. In: ECAI Workshop on Ontology Learning, vol. 61. Citeseer (2000)

    Google Scholar 

  62. Wa̧tróbski, J.: Ontology learning methods from text-an extensive knowledge-based approach. Proc. Comput. Sci. 176, 3356–3368 (2020)

    Google Scholar 

  63. Wei, J., et al.: Finetuned language models are zero-shot learners. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=gEZrGCozdqR

  64. Wei, J., et al.: Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)

  65. Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol. 35, pp. 24824–24837. Curran Associates, Inc. (2022). https://proceedings.neurips.cc/paper_files/paper/2022/file/9d5609613524ecf4f15af0f7b31abca4-Paper-Conference.pdf

  66. Weibel, S.L., Koch, T.: The dublin core metadata initiative. D-lib magazine 6(12), 1082–9873 (2000)

    Article  Google Scholar 

  67. Xu, F., Kurz, D., Piskorski, J., Schmeier, S.: A domain adaptive approach to automatic acquisition of domain relevant terms and their relations with bootstrapping. In: LREC (2002)

    Google Scholar 

  68. Yang, W., Zhang, H., Lin, J.: Simple applications of bert for ad hoc document retrieval (2019)

    Google Scholar 

  69. Yao, S., Yu, D., Zhao, J., Shafran, I., Griffiths, T.L., Cao, Y., Narasimhan, K.: Tree of thoughts: deliberate problem solving with large language models (2023)

    Google Scholar 

Download references

Acknowledgements

We thank the anonymous reviewers for their detailed and insightful comments on an earlier draft of the paper. This work was jointly supported by the German BMBF project SCINEXT (ID 01lS22070), DFG NFDI4DataScience (ID 460234259), and ERC ScienceGraph (ID 819536).

Author information

Authors and Affiliations

  1. TIB Leibniz Information Centre for Science and Technology, Hannover, Germany

    Hamed Babaei Giglou, Jennifer D’Souza & Sören Auer

Authors
  1. Hamed Babaei Giglou
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jennifer D’Souza
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sören Auer
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Hamed Babaei Giglou: Conceptualization, Methodology, Software, Validation, Investigation, Resources, Data Curation, Writing - Original Draft, Visualization. Jennifer D’Souza: Conceptualization, Methodology, Investigation, Resources, Writing - Original Draft, Writing - Review & Editing, Supervision, Project administration, Funding acquisition. Sören Auer: Conceptualization, Methodology, Investigation, Resources, Review & Editing, Supervision, Project administration, Funding acquisition.

Corresponding author

Correspondence to Hamed Babaei Giglou .

Editor information

Editors and Affiliations

  1. University of Liverpool, Liverpool, UK

    Terry R. Payne

  2. University of Bologna, Bologna, Italy

    Valentina Presutti

  3. Southeast University, Nanjing, China

    Guilin Qi

  4. Universidad Politécnica de Madrid, Madrid, Spain

    María Poveda-Villalón

  5. Huawei Technologies R&D UK, Edinburgh, UK

    Giorgos Stoilos

  6. Centrum Wiskunde and Informatica, Amsterdam, The Netherlands

    Laura Hollink

  7. IT University of Copenhagen, Copenhagen, Denmark

    Zoi Kaoudi

  8. Nanjing University, Nanjing, China

    Gong Cheng

  9. Tsinghua University, Beijing, Beijing, China

    Juanzi Li

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Babaei Giglou, H., D’Souza, J., Auer, S. (2023). LLMs4OL: Large Language Models for Ontology Learning. In: Payne, T.R., et al. The Semantic Web – ISWC 2023. ISWC 2023. Lecture Notes in Computer Science, vol 14265. Springer, Cham. https://doi.org/10.1007/978-3-031-47240-4_22

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-47240-4_22

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-47239-8

  • Online ISBN: 978-3-031-47240-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships

Search

Navigation