ELASTIC: numerical reasoning with adaptive symbolic compiler

Research output: Working paperWorking Paper/Preprint

21 Downloads (Pure)


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.
Original languageUndefined/Unknown
Place of PublicationIthaca, NY
Number of pages19
Publication statusSubmitted - 18 Oct 2022


  • numerical reasoning
  • adaptive symbolic compiler
  • ELASTIC: numerical reasoning with adaptive symbolic compiler

    Zhang, J. & Moshfeghi, Y., 9 Dec 2022, Advances in Neural Information Processing Systems 35: 36th Conference on Neural Information Processing Systems (NeurIPS 2022). Red Hook, NY, 20 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution book

    Open Access

Cite this