With the continuous development of artificial intelligence technology,deep learning methods have been widely used in the intelligent solution of math word problem.Graph-to-tree based encoder-decoder networks show good performance,but the lack of external knowledge limits the improvement of model solving accuracy.A detection module based on a geometric knowledge base was constructed and incorporated into the encoder-decoder net-work model to improve the predictive capability of the model.Through validation on the Chinese mathematical problem dataset GeometryQA,the model exhibits higher accuracy and has certain superiority.
关键词
自然语言处理/数学单词问题/几何知识库/检测模块
Key words
natural language processing/mathematical word problem/geometric knowledge base/detection network
维普
万方数据