Abstract
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.
Abstract (translated)
解决自动化几何数学问题求解中的挑战涉及理解和处理多模态信息和数学。现有方法在准确解释几何图方面遇到困难，这阻碍了有效的求解。为解决这个问题，我们提出了Geometry problem solver with natural Language Description (GOLD)模型。GOLD通过分别处理图中的符号和几何基本要素来增强提取几何关系。然后，它将提取的关系转换成自然语言描述，有效利用大型语言模型来解决几何数学问题。实验证明，GOLD模型在计算和证明子集的准确性上超过了UniGeo数据集上之前最佳方法的12.7%和42.1%。此外，它在PGPS9K和Geometry3K数据集以及PGPSNet上超过了最佳模型，分别获得了1.8%和3.2%的准确性提升。
URL
https://arxiv.org/abs/2405.00494
