A Goal-Driven Tree-Structured Neural Model for Math Word Problems

10 Aug 2019  ·  Zhipeng Xie and Shichao Sun ·

Most existing neural models for math word problems exploit Seq2Seq model to generate solution expressions sequentially from left to right, whose results are far from satisfactory due to the lack of goal-driven mechanism commonly seen in human problem solving. This paper proposes a treestructured neural model to generate expression tree in a goal-driven manner. Given a math word problem, the model first identifies and encodes its goal to achieve, and then the goal gets decomposed into sub-goals combined by an operator in a top-down recursive way. The whole process is repeated until the goal is simple enough to be realized by a known quantity as leaf node. During the process, two-layer gated-feedforward networks are designed to implement each step of goal decomposition, and a recursive neural network is used to encode fulfilled subtrees into subtree embeddings, which provides a better representation of subtrees than the simple goals of subtrees. Experimental results on the dataset Math23K have shown that our treestructured model outperforms significantly several state-of-the-art models.

PDF Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Math Word Problem Solving Math23K GTS Accuracy (5-fold) 74.3 # 12