ComSearch: Equation Searching with Combinatorial Mathematics for Solving Math Word Problems with Weak Supervision
Previous studies have introduced a weakly-supervised paradigm for solving math word problems requiring only the answer value annotation. While these methods search for correct value equation candidates as pseudo labels, they search among a narrow sub-space of the enormous equation space. To address this problem, we propose a novel search algorithm with combinatorial mathematics ComSearch, which can compress the search space by excluding mathematical equivalent equations. The compression allows the searching algorithm to enumerate all possible equations and obtain high-quality data. We investigate the noise in the pseudo labels that hold wrong mathematical logic, which we refer to as the false-matching problem, and propose a ranking model to denoise the pseudo labels. Our approach holds a flexible framework to utilize two existing supervised math word problem solvers to train pseudo labels, and both achieve state-of-the-art performance in the weak supervision task.
Code (0)
등록된 구현이 없습니다.
Tasks
MathSimilar Papers 제목 키워드 기반
ComSearch: Equation Searching with Combinatorial Mathematics for Solving Math Word Problems with Weak Supervision
Previous studies have introduced a weakly-supervised paradigm for solving math word problems requiring only the answer value annotation. While these methods search for correct value equation candidates as pseudo labels, …
MathComSearch: Equation Searching with Combinatorial Strategy for Solving Math Word Problems with Weak Supervision
Previous studies have introduced a weakly-supervised paradigm for solving math word problems requiring only the answer value annotation. While these methods search for correct value equation candidates as pseudo labels, …
MathCombiBench: Benchmarking LLM Capability for Combinatorial Mathematics
Neurosymbolic approaches integrating large language models with formal reasoning have recently achieved human-level performance on mathematics competition problems in algebra, geometry and number theory. In comparison, c…
BenchmarkingFrom Control to Mathematics-Part II: Observability-Based Design for Iterative Methods in Solving Linear Equations
The control approaches generally resort to the tools from the mathematics, but whether and how the mathematics can benefit from the control approaches is unclear. This paper aims to bring the "control design" idea into t…
Pretrained Language Models are Symbolic Mathematics Solvers too!
Solving symbolic mathematics has always been of in the arena of human ingenuity that needs compositional reasoning and recurrence. However, recent studies have shown that large-scale language models such as transformers …
IngenuityLanguage ModellingMath