Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic Library
This work addresses the problem of improving mathematical reasoning in neural systems, which is incremental as it builds on existing abductive learning and symbolic methods.
The paper tackles the challenge of neural mathematical reasoning by combining Transformer models with a symbolic mathematics library using an abductive learning framework, achieving a 9.73% accuracy improvement on interpolation tasks and 47.22% on extrapolation tasks over state-of-the-art methods.
Mathematical reasoning recently has been shown as a hard challenge for neural systems. Abilities including expression translation, logical reasoning, and mathematics knowledge acquiring appear to be essential to overcome the challenge. This paper demonstrates that some abilities can be achieved through abductive combination with discrete systems that have been programmed with human knowledge. On a mathematical reasoning dataset, we adopt the recently proposed abductive learning framework, and propose the ABL-Sym algorithm that combines the Transformer neural models with a symbolic mathematics library. ABL-Sym shows 9.73% accuracy improvement on the interpolation tasks and 47.22% accuracy improvement on the extrapolation tasks, over the state-of-the-art approaches. Online demonstration: http://math.polixir.ai