Math word problem generation via disentangled memory retrieval

• Main Authors: QIN, Wei, WANG, Xiaowei, HU, Zhenzhen, WANG, Lei, LAN, Yunshi, HONG, Richang
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2024
• Subjects: Memory; math word problem; retrieval; text generation; Artificial Intelligence and Robotics; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/lkcsb_research/7487; https://ink.library.smu.edu.sg/context/lkcsb_research/article/8486/viewcontent/MathWordProblem_av.pdf
• Institution: Singapore Management University

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.