Chapter 5. Answering Natural-Language Questions with Neuro-Symbolic Knowledge Bases

2021 ◽  
Author(s):  
Haitian Sun ◽  
Pat Verga ◽  
William W. Cohen

Symbolic reasoning systems based on first-order logics are computationally powerful, and feedforward neural networks are computationally efficient, so unless P=NP, neural networks cannot, in general, emulate symbolic logics. Hence bridging the gap between neural and symbolic methods requires achieving a delicate balance: one needs to incorporate just enough of symbolic reasoning to be useful for a task, but not so much as to cause computational intractability. In this chapter we first present results that make this claim precise, and then use these formal results to inform the choice of a neuro-symbolic knowledge-based reasoning system, based on a set-based dataflow query language. We then present experimental results with a number of variants of this neuro-symbolic reasoner, and also show that this neuro-symbolic reasoner can be closely integrated into modern neural language models.

2013 ◽  
Vol 1 (1) ◽  
pp. 158-178
Author(s):  
Urcun John Tanik

Cyberphysical system design automation utilizing knowledge based engineering techniques with globally networked knowledge bases can tremendously improve the design process for emerging systems. Our goal is to develop a comprehensive architectural framework to improve the design process for cyberphysical systems (CPS) and implement a case study with Axiomatic Design Solutions Inc. to develop next generation toolsets utilizing knowledge-based engineering (KBE) systems adapted to multiple domains in the field of CPS design automation. The Cyberphysical System Design Automation Framework (CPSDAF) will be based on advances in CPS design theory based on current research and knowledge collected from global sources automatically via Semantic Web Services. A case study utilizing STEM students is discussed.


2020 ◽  
Vol 53 (2) ◽  
pp. 1108-1113
Author(s):  
Magnus Malmström ◽  
Isaac Skog ◽  
Daniel Axehill ◽  
Fredrik Gustafsson

Author(s):  
Bjørn Magnus Mathisen ◽  
Kerstin Bach ◽  
Agnar Aamodt

AbstractAquaculture as an industry is quickly expanding. As a result, new aquaculture sites are being established at more exposed locations previously deemed unfit because they are more difficult and resource demanding to safely operate than are traditional sites. To help the industry deal with these challenges, we have developed a decision support system to support decision makers in establishing better plans and make decisions that facilitate operating these sites in an optimal manner. We propose a case-based reasoning system called aquaculture case-based reasoning (AQCBR), which is able to predict the success of an aquaculture operation at a specific site, based on previously applied and recorded cases. In particular, AQCBR is trained to learn a similarity function between recorded operational situations/cases and use the most similar case to provide explanation-by-example information for its predictions. The novelty of AQCBR is that it uses extended Siamese neural networks to learn the similarity between cases. Our extensive experimental evaluation shows that extended Siamese neural networks outperform state-of-the-art methods for similarity learning in this task, demonstrating the effectiveness and the feasibility of our approach.


Sign in / Sign up

Export Citation Format

Share Document