The task of math word problem (MWP) generation, which generates an MWP given an equation and relevant topic words, has increasingly attracted researchers’ attention. In this work, we introduce a simple memory retrieval module to search related training MWPs, which are used to augment the generation. To retrieve more relevant training data, we also propose a disentangled memory retrieval module based on the simple memory retrieval module. To this end, we first disentangle the training MWPs into logical description and scenario description and then record them in respective memory modules. Later, we use the given equation and topic words as queries to retrieve relevant logical descriptions and scenario descriptions from the corresponding memory modules, respectively. The retrieved results are then used to complement the process of the MWP generation. Extensive experiments and ablation studies verify the superior performance of our method and the effectiveness of each proposed module. The code is available at https://github.com/mwp-g/MWPG-DMR.

数学应用题（MWP）生成任务，即给定方程和相关主题词生成 MWP，越来越引起研究人员的关注。在这项工作中，我们引入了一个简单的内存检索模块来搜索相关的训练 MWP，用于增强生成。为了检索更多相关的训练数据，我们还提出了一种基于简单记忆检索模块的解缠结记忆检索模块。为此，我们首先将训练MWP分解为逻辑描述和场景描述，然后将它们记录在各自的内存模块中。随后，我们使用给定的方程和主题词作为查询，分别从相应的记忆模块中检索相关的逻辑描述和场景描述。然后，检索到的结果将用于补充 MWP 生成过程。大量的实验和消融研究验证了我们的方法的优越性能和每个提出的模块的有效性。该代码可从 https://github.com/mwp-g/MWPG-DMR 获取。