Neural-Symbolic Commonsense Reasoner with Relation Predictors

Abstract

Commonsense reasoning aims to incorporate sets of commonsense facts, retrieved from Commonsense Knowledge Graphs (CKG), to draw conclusion about ordinary situations. The dynamic nature of commonsense knowledge postulates models capable of performing multi-hop reasoning over new situations. This feature also results in having large-scale sparse Knowledge Graphs, where such reasoning process is needed to predict relations between new events. However, existing approaches in this area are limited by considering CKGs as a limited set of facts, thus rendering them unfit for reasoning over new unseen situations and events. In this paper, we present a neural-symbolic reasoner, which is capable of reasoning over large-scale dynamic CKGs. The logic rules for reasoning over CKGs are learned during training by our model. In addition to providing interpretable explanation, the learned logic rules help to generalise prediction to newly introduced events. Experimental results on the task of link prediction on CKGs prove the effectiveness of our model by outperforming the state-of-the-art models.

From LSAT: The Progress and Challenges of Complex Reasoning

“…They then utilize a neural module to learn continuous vectors for symbolic representations to deal with the uncertainty of data [75,76,20]. Specifically, for commonsense and multi-hop reasoning, the symbolic module can be designed to identify relevant knowledge and multi-hop reasoning chain, respectively, and then encode them into the neural module to match the answer [77,78,79,80]. However, how to generate high-quality programs under weak supervision and extract symbolic reasoning units in an unsupervised manner remains an elusive challenge.…”