Modelling symbolic knowledge using neural representations

Schockaert, Steven ORCID: https://orcid.org/0000-0002-9256-2881 and Gutierrez Basulto, Victor ORCID: https://orcid.org/0000-0002-6117-5459 2021. Modelling symbolic knowledge using neural representations. Presented at: Reasoning Web Summer School 2021, Leuven, Belgium, 8-15 September 2021. Reasoning Web. Lecture Notes in Computer Science Springer, pp. 59-75. 10.1007/978-3-030-95481-9_3

PDF - Accepted Post-Print Version Download (297kB)

Abstract

Symbolic reasoning and deep learning are two fundamentally different approaches to building AI systems, with complementary strengths and weaknesses. Despite their clear differences, however, the line between these two approaches is increasingly blurry. For instance, the neural language models which are popular in Natural Language Processing are increasingly playing the role of knowledge bases, while neural network learning strategies are being used to learn symbolic knowledge, and to develop strategies for reasoning more flexibly with such knowledge. This blurring of the boundary between symbolic and neural methods offers significant opportunities for developing systems that can combine the flexibility and inductive capabilities of neural networks with the transparency and systematic reasoning abilities of symbolic frameworks. At the same time, there are still many open questions around how such a combination can best be achieved. This paper presents an overview of recent work on the relationship between symbolic knowledge and neural representations, with a focus on the use of neural networks, and vector representations more generally, for encoding knowledge.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Publication
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	Springer
ISBN:	978-3-030-95480-2
Date of First Compliant Deposit:	25 October 2021
Date of Acceptance:	11 August 2021
Last Modified:	03 Jul 2025 13:43
URI:	https://orca.cardiff.ac.uk/id/eprint/144487

Actions (repository staff only)

Edit Item