Generalizing math word problem solvers via solution diversification

• Main Authors: LIANG, Zhenwen, ZHANG, Jipeng, WANG, Lei, WANG, Yan, SHAO, Jie, ZHANG, Xiangliang
• 格式: text
• 語言: English
• 出版: Institutional Knowledge at Singapore Management University 2023
• 主題: Question Answering; multiple solution equations; Argumentation; problem description; training framework; Artificial Intelligence and Robotics; Mathematics; Theory and Algorithms
• 在線閱讀: https://ink.library.smu.edu.sg/sis_research/8089; https://ink.library.smu.edu.sg/context/sis_research/article/9092/viewcontent/26548_pvoa.pdf
• 機構: Singapore Management University

Current math word problem (MWP) solvers are usually Seq2Seq models trained by the (one-problem; one-solution) pairs, each of which is made of a problem description and a solution showing reasoning flow to get the correct answer. However, one MWP problem naturally has multiple solution equations. The...