ELASTIC: Numerical Reasoning with Adaptive Symbolic Compiler
It addresses the problem of generating numerical reasoning programs for complex tasks in AI, offering a domain-agnostic solution with significant performance gains.
The paper tackles numerical reasoning over text by introducing ELASTIC, a model that separates operator and operand generation to handle complex tasks, achieving 68.96 execution accuracy and 65.21 program accuracy on FinQA and 83.00 program accuracy on MathQA, outperforming prior state-of-the-art models.
Numerical reasoning over text is a challenging task of Artificial Intelligence (AI), requiring reading comprehension and numerical reasoning abilities. Previous approaches use numerical reasoning programs to represent the reasoning process. However, most works do not separate the generation of operators and operands, which are key components of a numerical reasoning program, thus limiting their ability to generate such programs for complicated tasks. In this paper, we introduce the numEricaL reASoning with adapTive symbolIc Compiler (ELASTIC) model, which is constituted of the RoBERTa as the Encoder and a Compiler with four modules: Reasoning Manager, Operator Generator, Operands Generator, and Memory Register. ELASTIC is robust when conducting complicated reasoning. Also, it is domain agnostic by supporting the expansion of diverse operators without caring about the number of operands it contains. Experiments show that ELASTIC achieves 68.96 and 65.21 of execution accuracy and program accuracy on the FinQA dataset and 83.00 program accuracy on the MathQA dataset, outperforming previous state-of-the-art models significantly.