Solving Math Word Problems Following Logically Consistent Template
2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN(2023)
摘要
Solving math word problems (MWPs) is a challenging task. Some existing solvers retrieve textually similar problems and draw on their solutions to solve the given problem. However, textually similar questions are not guaranteed to have similar solutions, and vice versa. Therefore, this work investigates the logical consistency among different problems and proposes a novel framework to solve math word problems following logically consistent templates. Experimental results show that our method outperforms many strong baselines, including some pre-trained language model-based methods. Further analysis shows that our retrieval method does learn the logical similarity between questions and plays a crucial role in our model's performance.
更多查看译文
关键词
Natural Language Processing,MathWord Problems,Contrastive Learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要