Enhancing Neural Mathematical Reasoning by Abductive Combination with Symbolic Library

03/28/2022
by   Yangyang Hu, et al.
0

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 extrapolation tasks, over the state-of-the-art approaches. Online demonstration: http://math.polixir.ai

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/20/2020

Adventures in Mathematical Reasoning

"Mathematics is not a careful march down a well-cleared highway, but a j...
research
04/02/2019

Analysing Mathematical Reasoning Abilities of Neural Models

Mathematical reasoning---a core ability within human intelligence---pres...
research
02/11/2023

Learning by Applying: A General Framework for Mathematical Reasoning via Enhancing Explicit Knowledge Learning

Mathematical reasoning is one of the crucial abilities of general artifi...
research
09/19/2022

Knowledge-based Analogical Reasoning in Neuro-symbolic Latent Spaces

Analogical Reasoning problems challenge both connectionist and symbolic ...
research
02/04/2018

Tunneling Neural Perception and Logic Reasoning through Abductive Learning

Perception and reasoning are basic human abilities that are seamlessly c...
research
07/06/2022

Extending Logical Neural Networks using First-Order Theories

Logical Neural Networks (LNNs) are a type of architecture which combine ...
research
06/13/2020

Modelling High-Level Mathematical Reasoning in Mechanised Declarative Proofs

Mathematical proofs can be mechanised using proof assistants to eliminat...

Please sign up or login with your details

Forgot password? Click here to reset