Teacher-Student Networks with Multiple Decoders for Solving Math Word Problem

By Jipeng Zhang, Roy Ka-Wei Lee, Ee-Peng Lim, Wei Qin, Lei Wang, Jie Shao, Qianru Sun. 2020

72 citations recorded by the source corpus.

Math word problem (MWP) is challenging due to the limitation in training data where only one “standard” solution is available. MWP models often simply fit this solution rather than truly understand or solve the problem. The generalization of models (to diverse word scenarios) is thus limited. To address this problem, this paper proposes a novel approach, TSN-MD, by leveraging the teacher network to integrate the knowledge of equivalent solution expressions and then to regularize the learning behavior of the student network. In addition, we introduce the multiple-decoder student network to generate multiple candidate solution expressions by which the final answer is voted. In experiments, we conduct extensive comparisons and ablative studies on two large-scale MWP benchmarks, and show that using TSN-MD can surpass the state-of-the-art works by a large margin. More intriguingly, the visualization results demonstrate that TSN-MD not only produces correct final answers but also generates diverse equivalent expressions of the solution.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xiaodan Liang
2. Xiangliang Zhang
3. Zhenwen Liang
4. Liang Lin
5. Jie Shao
6. Xuanjing Huang
7. Qi Zhang
8. Qinzhuo Wu

In Information Systems

1. Zhenwen Liang
2. Xiangliang Zhang
3. Qinzhuo Wu
4. Yining Hong
5. Liang Lin
6. Xuanjing Huang
7. Jie Shao
8. Zhongyu Wei

Citations in the corpus

• TM-generation model: a template-based method for automatically solving mathematical word problems (2021, methodology): “As in other studies [4, 7, 23], we defined problem-solving accuracy as the proportion of correctly solved problems over the total number of problems.”
• MWP-BERT: A Strong Baseline for Math Word Problems (2021, methodology): “To avoid the implementation error that may cause unreproducible results of baseline models, we reported the results of these baselines from the papers where they were published, as many previous papers (Zhang et al., 2020b; Shen and Jin, 2020) did.”
• Math Word Problem Solving with Explicit Numerical Values (2021, methodology): “To better utilize expression structure information, recent studies have used Seq2Tree models (Liu et al., 2019; Zhang et al., 2020a).”
• A Survey of Deep Learning for Mathematical Reasoning (2022, unknown): “Recent studies have shown that these tokenization approaches are suboptimal (Wallace et al., 2019; Lin et al., 2020; Zhang et al., 2020d; Thawani et al., 2022).”
• Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks (2021, background): “Comparing with TSN-MD, our solver outperforms it by about 0.6% on Math23K.”
• Solving Math Word Problems with Teacher Supervision (2021, methodology): “Graph2Tree [ Zhang et al. , 2020b ] trained by samples including Problem1 gives a wrong so-lution to Problem2.”