Papers
Topics
Authors
Recent
Search
2000 character limit reached

Sandra -- A Neuro-Symbolic Reasoner Based On Descriptions And Situations

Published 1 Feb 2024 in cs.AI | (2402.00591v3)

Abstract: This paper presents sandra, a neuro-symbolic reasoner combining vectorial representations with deductive reasoning. Sandra builds a vector space constrained by an ontology and performs reasoning over it. The geometric nature of the reasoner allows its combination with neural networks, bridging the gap with symbolic knowledge representations. Sandra is based on the Description and Situation (DnS) ontology design pattern, a formalization of frame semantics. Given a set of facts (a situation) it allows to infer all possible perspectives (descriptions) that can provide a plausible interpretation for it, even in presence of incomplete information. We prove that our method is correct with respect to the DnS model. We experiment with two different tasks and their standard benchmarks, demonstrating that, without increasing complexity, sandra (i) outperforms all the baselines (ii) provides interpretability in the classification process, and (iii) allows control over the vector space, which is designed a priori.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. Knowledge graph construction with a façade: A unified method to access heterogeneous data sources on the web. ACM Trans. Internet Technol., 2022.
  2. Measuring abstract reasoning in neural networks. In International conference on machine learning, pages 511–520. PMLR, 2018.
  3. Rdf 1.1 turtle. World Wide Web Consortium, pages 18–31, 2014.
  4. A challenge for historical research: Making data fair using a collaborative ontology management environment (ontome). Semant. Web, 12(2):279–294, jan 2021.
  5. Integrating ontologies and vector space embeddings using conceptual spaces. International Research School in Artificial Intelligence in Bergen, 99:3, 2022.
  6. Boyan Brodaric and Femke Reitsma and Yi Qiang. SKIing with DOLCE : toward an e-Science knowledge infrastructure. In Carola Eschenbach and Michael Gruninger, editor, Frontiers in Artificial Intelligence and Applications, volume 183, pages 208–219. IOS Press, 2008.
  7. Owl2vec*: embedding of OWL ontologies. Mach. Learn., 110(7):1813–1845, 2021.
  8. Towards bridging the neuro-symbolic gap: deep deductive reasoners. Appl. Intell., 51(9):6326–6348, 2021.
  9. Charles J Fillmore et al. Frame semantics. Cognitive linguistics: Basic readings, 34:373–400, 2006.
  10. Understanding the semantic web through descriptions and situations. In OTM Confederated International Conferences” On the Move to Meaningful Internet Systems”, pages 689–706. Springer, 2003.
  11. Peter Gardenfors. Conceptual spaces: The geometry of thought. MIT press, 2004.
  12. dpasp: A comprehensive differentiable probabilistic answer set programming environment for neurosymbolic learning and reasoning. arXiv preprint arXiv:2308.02944, 2023.
  13. Hermit: An OWL 2 reasoner. J. Autom. Reason., 53(3):245–269, 2014.
  14. Deep sparse rectifier neural networks. In Geoffrey J. Gordon, David B. Dunson, and Miroslav Dudík, editors, Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2011, Fort Lauderdale, USA, April 11-13, 2011, volume 15 of JMLR Proceedings, pages 315–323. JMLR.org, 2011.
  15. Hierarchical convit with attention-based relational reasoner for visual analogical reasoning. In Brian Williams, Yiling Chen, and Jennifer Neville, editors, Thirty-Seventh AAAI Conference on Artificial Intelligence, AAAI 2023, Thirty-Fifth Conference on Innovative Applications of Artificial Intelligence, IAAI 2023, Thirteenth Symposium on Educational Advances in Artificial Intelligence, EAAI 2023, Washington, DC, USA, February 7-14, 2023, pages 22–30. AAAI Press, 2023.
  16. A neuro-vector-symbolic architecture for solving raven’s progressive matrices. Nat. Mac. Intell., 5(4):363–375, 2023.
  17. Owl 2 web ontology language manchester syntax. W3C Working Group Note, 2009.
  18. Stratified rule-aware network for abstract visual reasoning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 1567–1574, 2021.
  19. Norihiro Kamide. Reasoning with inconsistency-tolerant fuzzy description logics. In Ana Paula Rocha, Luc Steels, and H. Jaap van den Herik, editors, Proceedings of the 14th International Conference on Agents and Artificial Intelligence, ICAART 2022, Volume 3, Online Streaming, February 3-5, 2022, pages 63–74. SCITEPRESS, 2022.
  20. Deep learning. Nat., 521(7553):436–444, 2015.
  21. Domain generalization using causal matching. In International Conference on Machine Learning, pages 7313–7324. PMLR, 2021.
  22. Deep learning methods for abstract visual reasoning: A survey on raven’s progressive matrices. arXiv preprint arXiv:2201.12382, 2022.
  23. Deepproblog: Neural probabilistic logic programming. Advances in neural information processing systems, 31, 2018.
  24. Matrix analysis and applied linear algebra. SIAM, 2023.
  25. Marvin Minsky. A framework for representing knowledge, 1974.
  26. Cone semantics for logics with negation. In IJCAI, pages 1820–1826, 2020.
  27. What say you: An ontological representation of imperative meaning for human-robot interaction. In Joint Ontology Workshops, 2020.
  28. A simple neural network module for relational reasoning. Advances in neural information processing systems, 30, 2017.
  29. Measuring abstract reasoning in neural networks. In Jennifer G. Dy and Andreas Krause, editors, Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10-15, 2018, volume 80 of Proceedings of Machine Learning Research, pages 4477–4486. PMLR, 2018.
  30. F–a model of events based on the foundational ontology dolce+dns ultralight. In Proceedings of the Fifth International Conference on Knowledge Capture, K-CAP ’09, page 137–144, New York, NY, USA, 2009. Association for Computing Machinery.
  31. A-nesi: A scalable approximate method for probabilistic neurosymbolic inference. arXiv preprint arXiv:2212.12393, 2022.
  32. An empirical investigation of domain generalization with empirical risk minimizers. In Marc’Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan, editors, Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, pages 28131–28143, 2021.
  33. Creating a More Transparent Internet. Studies in Natural Language Processing. Cambridge University Press, 2022.
  34. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:2308.02944, 2017.
  35. Abstract visual reasoning: An algebraic approach for solving raven’s progressive matrices. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6715–6724, 2023.
  36. RAVEN: A dataset for relational and analogical visual reasoning. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pages 5317–5327. Computer Vision Foundation / IEEE, 2019.
  37. Learning perceptual inference by contrasting. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d’Alché-Buc, Emily B. Fox, and Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pages 1073–1085, 2019.
  38. Abstract spatial-temporal reasoning via probabilistic abduction and execution. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021, pages 9736–9746. Computer Vision Foundation / IEEE, 2021.
  39. Abstract reasoning with distracting features. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d’Alché-Buc, Emily B. Fox, and Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pages 5834–5845, 2019.
  40. Domain generalization: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
  41. Domain generalization: A survey. IEEE Trans. Pattern Anal. Mach. Intell., 45(4):4396–4415, 2023.
  42. Effective abstract reasoning with dual-contrast network. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021.
  43. Unsupervised abstract reasoning for raven’s problem matrices. IEEE Trans. Image Process., 30:8332–8341, 2021.
Citations (4)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now