On the Capabilities of Pointer Networks for Deep Deductive Reasoning
This addresses the challenge of developing accurate and generalizable neuro-symbolic reasoners for AI systems, representing an incremental advance with novel application.
The paper tackles the problem of building neural networks for deductive reasoning over symbolic knowledge bases by applying pointer networks, achieving significant performance improvements over previous state-of-the-art methods across multiple reasoning tasks.
The importance of building neural networks that can learn to reason has been well recognized in the neuro-symbolic community. In this paper, we apply neural pointer networks for conducting reasoning over symbolic knowledge bases. In doing so, we explore the benefits and limitations of encoder-decoder architectures in general and pointer networks in particular for developing accurate, generalizable and robust neuro-symbolic reasoners. Based on our experimental results, pointer networks performs remarkably well across multiple reasoning tasks while outperforming the previously reported state of the art by a significant margin. We observe that the Pointer Networks preserve their performance even when challenged with knowledge graphs of the domain/vocabulary it has never encountered before. To the best of our knowledge, this is the first study on neuro-symbolic reasoning using Pointer Networks. We hope our impressive results on these reasoning problems will encourage broader exploration of pointer networks' capabilities for reasoning over more complex logics and for other neuro-symbolic problems.