Addressing the challenge of automated geometry math problem-solving in artificial intelligence (AI) involves understanding multi-modal information and mathematics. Current methods struggle with accurately interpreting geometry diagrams, which hinders effective problem-solving. To tackle this issue, we present the Geometry problem sOlver with natural Language Description (GOLD) model. GOLD enhances the extraction of geometric relations by separately processing symbols and geometric primitives within the diagram. Subsequently, it converts the extracted relations into natural language descriptions, efficiently utilizing large language models to solve geometry math problems. Experiments show that the GOLD model outperforms the Geoformer model, the previous best method on the UniGeo dataset, by achieving accuracy improvements of 12.7% and 42.1% in calculation and proving subsets. Additionally, it surpasses the former best model on the PGPS9K and Geometry3K datasets, PGPSNet, by obtaining accuracy enhancements of 1.8% and 3.2%, respectively.

翻译：在人工智能中解决自动几何数学问题这一挑战，涉及对多模态信息与数学的理解。当前方法在准确解读几何图形方面存在困难，这阻碍了问题的有效求解。为解决此问题，我们提出了基于自然语言描述的几何问题求解器（GOLD）模型。GOLD通过分别处理图形中的符号与几何基元，增强了几何关系的提取能力。随后，它将提取的关系转化为自然语言描述，高效利用大型语言模型求解几何数学问题。实验表明，GOLD模型在UniGeo数据集的计算与证明子集上分别实现了12.7%和42.1%的准确率提升，优于此前最优方法Geoformer模型。此外，它在PGPS9K和Geometry3K数据集上分别以1.8%和3.2%的准确率优势超越此前最佳模型PGPSNet。