Integrating Ontologies and Vector Space Embeddings Using Conceptual Spaces (Invited Paper)

Authors Zied Bouraoui, Víctor Gutiérrez-Basulto , Steven Schockaert



PDF
Thumbnail PDF

File

OASIcs.AIB.2022.3.pdf
  • Filesize: 2.16 MB
  • 30 pages

Document Identifiers

Author Details

Zied Bouraoui
  • CRIL Laboratory, Université d'Artois, Arras, France
Víctor Gutiérrez-Basulto
  • School of Computer Science & Informatics, Cardiff University, UK
Steven Schockaert
  • School of Computer Science & Informatics, Cardiff University, UK

Cite AsGet BibTex

Zied Bouraoui, Víctor Gutiérrez-Basulto, and Steven Schockaert. Integrating Ontologies and Vector Space Embeddings Using Conceptual Spaces (Invited Paper). In International Research School in Artificial Intelligence in Bergen (AIB 2022). Open Access Series in Informatics (OASIcs), Volume 99, pp. 3:1-3:30, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2022)
https://doi.org/10.4230/OASIcs.AIB.2022.3

Abstract

Ontologies and vector space embeddings are among the most popular frameworks for encoding conceptual knowledge. Ontologies excel at capturing the logical dependencies between concepts in a precise and clearly defined way. Vector space embeddings excel at modelling similarity and analogy. Given these complementary strengths, there is a clear need for frameworks that can combine the best of both worlds. In this paper, we present an overview of our recent work in this area. We first discuss the theory of conceptual spaces, which was proposed in the 1990s by Gärdenfors as an intermediate representation layer in between embeddings and symbolic knowledge bases. We particularly focus on a number of recent strategies for learning conceptual space representations from data. Next, building on the idea of conceptual spaces, we discuss approaches where relational knowledge is modelled in terms of geometric constraints. Such approaches aim at a tight integration of symbolic and geometric representations, which unfortunately comes with a number of limitations. For this reason, we finally also discuss methods in which similarity, and other forms of conceptual relatedness, are derived from vector space embeddings and subsequently used to support flexible forms of reasoning with ontologies, thus enabling a looser integration between embeddings and symbolic knowledge.

Subject Classification

ACM Subject Classification
  • Computing methodologies → Knowledge representation and reasoning
Keywords
  • Conceptual Spaces
  • Ontologies
  • Vector Space Embeddings
  • Learning and Reasoning

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads

References

  1. Ralph Abboud, İsmail İlkan Ceylan, Thomas Lukasiewicz, and Tommaso Salvatori. BoxE: A box embedding model for knowledge base completion. In NeurIPS, 2020. Google Scholar
  2. Thomas Ager. Disentangling low-dimensional vector space representations of text documents. PhD thesis, Cardiff University, 2021. Google Scholar
  3. Thomas Ager, Ondrej Kuzelka, and Steven Schockaert. Modelling salient features as directions in fine-tuned semantic spaces. In CoNLL, pages 530-540, 2018. Google Scholar
  4. Rana Alshaikh, Zied Bouraoui, Shelan S. Jeawak, and Steven Schockaert. A mixture-of-experts model for learning multi-facet entity embeddings. In COLING, pages 5124-5135, 2020. Google Scholar
  5. Rana Alshaikh, Zied Bouraoui, and Steven Schockaert. Learning conceptual spaces with disentangled facets. In CoNLL, pages 131-139, 2019. Google Scholar
  6. Rana Alshaikh, Zied Bouraoui, and Steven Schockaert. Hierarchical linear disentanglement of data-driven conceptual spaces. In IJCAI, pages 3573-3579, 2020. Google Scholar
  7. Abhijeet Awasthi, Sabyasachi Ghosh, Rasna Goyal, and Sunita Sarawagi. Learning from rules generalizing labeled exemplars. In ICLR, 2020. Google Scholar
  8. Franz Baader, Sebastian Brandt, and Carsten Lutz. Pushing the EL envelope. In IJCAI, pages 364-369, 2005. Google Scholar
  9. Franz Baader, Ian Horrocks, Carsten Lutz, and Ulrike Sattler. An Introduction to Description Logic. Cambridge University Press, 2017. Google Scholar
  10. Jean-François Baget, Michel Leclère, Marie-Laure Mugnier, and Eric Salvat. On rules with existential variables: Walking the decidability line. Artif. Intell., 175(9-10):1620-1654, 2011. Google Scholar
  11. Nelly Barbot, Laurent Miclet, and Henri Prade. Analogy between concepts. Artificial Intelligence, 275:487-539, 2019. Google Scholar
  12. Sabri Bayoudh, Laurent Miclet, and Arnaud Delhay. Learning by analogy: A classification rule for binary and nominal data. In IJCAI, pages 678-683, 2007. Google Scholar
  13. Islam Beltagy, Cuong Chau, Gemma Boleda, Dan Garrette, Katrin Erk, and Raymond J. Mooney. Montague meets Markov: Deep semantics with probabilistic logical form. In *SEM, pages 11-21, 2013. Google Scholar
  14. Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Weston, and Oksana Yakhnenko. Translating embeddings for modeling multi-relational data. In NIPS, pages 2787-2795, 2013. Google Scholar
  15. Stefan Borgwardt, İsmail İlkan Ceylan, and Thomas Lukasiewicz. Recent advances in querying probabilistic knowledge bases. In IJCAI, pages 5420-5426, 2018. Google Scholar
  16. Zied Bouraoui, José Camacho-Collados, Luis Espinosa Anke, and Steven Schockaert. Modelling semantic categories using conceptual neighborhood. In AAAI, pages 7448-7455. AAAI Press, 2020. Google Scholar
  17. Zied Bouraoui, Shoaib Jameel, and Steven Schockaert. Inductive reasoning about ontologies using conceptual spaces. In AAAI, pages 4364-4370, 2017. Google Scholar
  18. Zied Bouraoui and Steven Schockaert. Learning conceptual space representations of interrelated concepts. In Jérôme Lang, editor, IJCAI, pages 1760-1766, 2018. Google Scholar
  19. Camille Bourgaux, Ana Ozaki, and Jeff Z. Pan. Geometric models for (temporally) attributed description logics. In Martin Homola, Vladislav Ryzhikov, and Renate A. Schmidt, editors, DL, 2021. Google Scholar
  20. Katarina Britz, Thomas Meyer, and Ivan Varzinczak. Semantic foundation for preferential description logics. In Australasian Joint Conference on Artificial Intelligence, pages 491-500. Springer, 2011. Google Scholar
  21. Andrea Calì, Georg Gottlob, and Michael Kifer. Taming the infinite chase: Query answering under expressive relational constraints. J. Artif. Intell. Res., 48:115-174, 2013. Google Scholar
  22. José Camacho-Collados, Mohammad Taher Pilehvar, and Roberto Navigli. Nasari: Integrating explicit knowledge and corpus statistics for a multilingual representation of concepts and entities. Artificial Intelligence, 240:36-64, 2016. Google Scholar
  23. Claudia d'Amato, Nicola Fanizzi, Bettina Fazzinga, Georg Gottlob, and Thomas Lukasiewicz. Ontology-based semantic search on the web and its combination with the power of inductive reasoning. Ann. Math. Artif. Intell., 65(2-3):83-121, 2012. Google Scholar
  24. Thomas Demeester, Tim Rocktäschel, and Sebastian Riedel. Lifted rule injection for relation embeddings. In EMNLP, pages 1389-1399, 2016. Google Scholar
  25. Joaquín Derrac and Steven Schockaert. Inducing semantic relations from conceptual spaces: A data-driven approach to plausible reasoning. Artif. Intell., 228:66-94, 2015. Google Scholar
  26. Didier Dubois, Henri Prade, Francesc Esteva, Pere Garcia, and Lluis Godo. A logical approach to interpolation based on similarity relations. International Journal of Approximate Reasoning, 17(1):1-36, 1997. Google Scholar
  27. Peter Gärdenfors. Conceptual spaces: The geometry of thought. MIT press, 2000. Google Scholar
  28. Peter Gärdenfors. How to make the semantic web more semantic. In A.C. Varzi and L. Vieu, editors, Formal Ontology in Information Systems, pages 19-36. IOS Press, 2004. Google Scholar
  29. Peter Gärdenfors. The geometry of meaning: Semantics based on conceptual spaces. MIT press, 2014. Google Scholar
  30. Peter Gärdenfors and Mary-Anne Williams. Reasoning about categories in conceptual spaces. In IJCAI, pages 385-392, 2001. Google Scholar
  31. Dedre Gentner. Structure-mapping: A theoretical framework for analogy. Cognitive science, 7(2):155-170, 1983. Google Scholar
  32. Laura Giordano, Valentina Gliozzi, Nicola Olivetti, and Gian Luca Pozzato. Semantic characterization of rational closure: From propositional logic to description logics. Artificial Intelligence, 226:1-33, 2015. Google Scholar
  33. Robert L Goldstone. Isolated and interrelated concepts. Memory & Cognition, 24(5):608-628, 1996. Google Scholar
  34. Nelson Goodman. Fact, fiction, and forecast. Harvard University Press, 1955. Google Scholar
  35. Georg Gottlob, Michael Morak, and Andreas Pieris. Recent advances in datalog±. In Reasoning Web, volume 9203 of Lecture Notes in Computer Science, pages 193-217, 2015. Google Scholar
  36. Víctor Gutiérrez-Basulto, Jean Christoph Jung, Carsten Lutz, and Lutz Schröder. Probabilistic description logics for subjective uncertainty. J. Artif. Intell. Res., 58:1-66, 2017. Google Scholar
  37. Víctor Gutiérrez-Basulto and Steven Schockaert. From knowledge graph embedding to ontology embedding? an analysis of the compatibility between vector space representations and rules. In KR, pages 379-388, 2018. Google Scholar
  38. Douglas R Hofstadter, Melanie Mitchell, et al. The copycat project: A model of mental fluidity and analogy-making. Advances in Connectionist and Neural Computation Theory, 2:205-267, 1995. Google Scholar
  39. Keith J Holyoak and Paul Thagard. The analogical mind. American psychologist, 52(1):35-44, 1997. Google Scholar
  40. Nicolas Hug, Henri Prade, Gilles Richard, and Mathieu Serrurier. Analogical classifiers: A theoretical perspective. In ECAI, pages 689-697, 2016. Google Scholar
  41. Yazmín Ibáñez-García, Víctor Gutiérrez-Basulto, and Steven Schockaert. Plausible reasoning about el-ontologies using concept interpolation. In KR, pages 506-516, 2020. Google Scholar
  42. Sarit Kraus, Daniel Lehmann, and Menachem Magidor. Nonmonotonic reasoning, preferential models and cumulative logics. Artificial intelligence, 44(1-2):167-207, 1990. Google Scholar
  43. Tao Li and Vivek Srikumar. Augmenting neural networks with first-order logic. In ACL, pages 292-302, 2019. Google Scholar
  44. Robin Manhaeve, Sebastijan Dumancic, Angelika Kimmig, Thomas Demeester, and Luc De Raedt. DeepProbLog: Neural probabilistic logic programming. In NeurIPS, pages 3753-3763, 2018. Google Scholar
  45. Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. Linguistic regularities in continuous space word representations. In NAACL-HLT, pages 746-751, 2013. Google Scholar
  46. Roberto Navigli and Simone Paolo Ponzetto. Babelnet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network. Artificial Intelligence, 193:217-250, 2012. Google Scholar
  47. Maximilian Nickel, Volker Tresp, and Hans-Peter Kriegel. A three-way model for collective learning on multi-relational data. In ICML, pages 809-816, 2011. Google Scholar
  48. Maximillian Nickel and Douwe Kiela. Poincaré embeddings for learning hierarchical representations. NIPS, 30:6338-6347, 2017. Google Scholar
  49. Robert M Nosofsky. Choice, similarity, and the context theory of classification. Journal of Experimental Psychology: Learning, Memory, and Cognition, 10(1):104-114, 1984. Google Scholar
  50. Daniel N Osherson, Edward E Smith, Ormond Wilkie, Alejandro Lopez, and Eldar Shafir. Category-based induction. Psychological Review, 97(2):185-200, 1990. Google Scholar
  51. Matías Osta-Vélez and Peter Gärdenfors. Category-based induction in conceptual spaces. Journal of Mathematical Psychology, 96, 2020. Google Scholar
  52. Özgür Lütfü Özçep, Mena Leemhuis, and Diedrich Wolter. Cone semantics for logics with negation. In IJCAI, pages 1820-1826, 2020. Google Scholar
  53. Jeffrey Pennington, Richard Socher, and Christopher D. Manning. GloVe: Global vectors for word representation. In EMNLP, pages 1532-1543, 2014. Google Scholar
  54. Henri Prade and Gilles Richard, editors. Computational Approaches to Analogical Reasoning: Current Trends, volume 548 of Studies in Computational Intelligence. Springer, 2014. Google Scholar
  55. Henri Prade and Gilles Richard. From analogical proportion to logical proportions: A survey. In Computational Approaches to Analogical Reasoning: Current Trends, pages 217-244. Springer, 2014. Google Scholar
  56. Meng Qu, Junkun Chen, Louis-Pascal Xhonneux, Yoshua Bengio, and Jian Tang. Rnnlogic: Learning logic rules for reasoning on knowledge graphs. In ICLR, 2020. Google Scholar
  57. W.V. Quine. From a Logical Point of View. Harvard University Press, 1953. Google Scholar
  58. Lance J Rips. Inductive judgments about natural categories. Journal of Verbal Learning and Verbal Behavior, 14(6):665-681, 1975. Google Scholar
  59. Tim Rocktäschel and Sebastian Riedel. End-to-end differentiable proving. In NIPS, pages 3788-3800, 2017. Google Scholar
  60. Andrea Rossi, Denilson Barbosa, Donatella Firmani, Antonio Matinata, and Paolo Merialdo. Knowledge graph embedding for link prediction: A comparative analysis. ACM Transactions on Knowledge Discovery from Data, 15(2):1-49, 2021. Google Scholar
  61. Steven Schockaert, Yazmín Ibáñez-García, and Víctor Gutiérrez-Basulto. A description logic for analogical reasoning. In IJCAI, pages 2040-2046. ijcai.org, 2021. Google Scholar
  62. Steven Schockaert, Yazmín Angélica Ibáñez-García, and Víctor Gutiérrez-Basulto. Modelling concept interpolation in description logics using abstract betweenness relations. In DL, 2021. Google Scholar
  63. Steven Schockaert and Henri Prade. Solving conflicts in information merging by a flexible interpretation of atomic propositions. Artif. Intell., 175(11):1815-1855, 2011. Google Scholar
  64. Steven Schockaert and Henri Prade. Interpolative and extrapolative reasoning in propositional theories using qualitative knowledge about conceptual spaces. Artif. Intell., 202:86-131, 2013. Google Scholar
  65. Mikhail Sheremet, Dmitry Tishkovsky, Frank Wolter, and Michael Zakharyaschev. A logic for concepts and similarity. Journal of Logic and Computation, 17(3):415-452, 2007. Google Scholar
  66. Steven A Sloman. Feature-based induction. Cognitive Psychology, 25(2):231-280, 1993. Google Scholar
  67. Gustav Sourek, Vojtech Aschenbrenner, Filip Zelezný, Steven Schockaert, and Ondrej Kuzelka. Lifted relational neural networks: Efficient learning of latent relational structures. J. Artif. Intell. Res., 62:69-100, 2018. Google Scholar
  68. Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. Rotate: Knowledge graph embedding by relational rotation in complex space. In ICLR, 2018. Google Scholar
  69. Zhiqing Sun, Zhi-Hong Deng, Jian-Yun Nie, and Jian Tang. RotatE: Knowledge graph embedding by relational rotation in complex space. In ICLR, 2019. Google Scholar
  70. Théo Trouillon, Christopher R. Dance, Éric Gaussier, Johannes Welbl, Sebastian Riedel, and Guillaume Bouchard. Knowledge graph completion via complex tensor factorization. J. Mach. Learn. Res., 18:130:1-130:38, 2017. Google Scholar
  71. Asahi Ushio, José Camacho-Collados, and Steven Schockaert. Distilling relation embeddings from pretrained language models. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih, editors, EMNLP, pages 9044-9062, 2021. Google Scholar
  72. Quan Wang, Zhendong Mao, Bin Wang, and Li Guo. Knowledge graph embedding: A survey of approaches and applications. IEEE Transactions on Knowledge and Data Engineering, 29(12):2724-2743, 2017. Google Scholar
  73. Rudolf Wille. Restructuring lattice theory: An approach based on hierarchies of concepts. In Ordered Sets, pages 445-470. Springer, 1982. Google Scholar
  74. Jingyi Xu, Zilu Zhang, Tal Friedman, Yitao Liang, and Guy Van den Broeck. A semantic loss function for deep learning with symbolic knowledge. In ICML, pages 5498-5507, 2018. Google Scholar
  75. Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. Embedding entities and relations for learning and inference in knowledge bases. In ICLR, 2015. Google Scholar
  76. Bishan Yang, Wen-tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. Embedding entities and relations for learning and inference in knowledge bases. In ICLR, 2015. Google Scholar
  77. Zhun Yang, Adam Ishay, and Joohyung Lee. Neurasp: Embracing neural networks into answer set programming. In IJCAI, pages 1755-1762, 2020. Google Scholar
  78. LA Zadeh. Calculus of fuzzy restrictions. In Fuzzy Sets and Their Applications to Cognitive and Decision Processes: Proceedings of the US-Japan Seminar on Fuzzy Sets and Their Applications, Held at the University of California, Berkeley, California, July 1-4, 1974, pages 1-39, 1975. Google Scholar
  79. Zhanqiu Zhang, Jie Wang, Jiajun Chen, Shuiwang Ji, and Feng Wu. ConE: Cone embeddings for multi-hop reasoning over knowledge graphs. NeurIPS, 2021. Google Scholar
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail