Clause-level Relationship-aware Math Word Problems Solver

Abstract

Automatically solving math word problems, which involves comprehension, cognition, and reasoning, is a crucial issue in artificial intelligence research. Existing math word problem solvers mainly work on word-level relationship extraction and the generation of expression solutions while lacking consideration of the clause-level relationship. To this end, inspired by the theory of two levels of process in comprehension, we propose a novel clause-level relationship-aware math solver (CLRSolver) to mimic the process of human comprehension from lower level to higher level. Specifically, in the lower-level processes, we split problems into clauses according to their natural division and learn their semantics. In the higher-level processes, following human′s multi-view understanding of clause-level relationships, we first apply a CNN-based module to learn the dependency relationships between clauses from word relevance in a local view. Then, we propose two novel relationship-aware mechanisms to learn dependency relationships from the clause semantics in a global view. Next, we enhance the representation of clauses based on the learned clause-level dependency relationships. In expression generation, we develop a tree-based decoder to generate the mathematical expression. We conduct extensive experiments on two datasets, where the results demonstrate the superiority of our framework.