Recently, graph-based deep learning models have exhibited remarkable performance in generating solution expressions for the math word problem (MWP). However, most of these models have not taken into account the limitations and errors in constructing prior knowledge graphs, which may affect their accuracy and reliability in practical applications. In addition, during graph learning, they focus on extracting information from each given graph, while neglecting the adaptability and unification of graph representation learning. In this paper, we propose a novel multi-view graph learning-to-tree model with dual-strategy (MVG-DS-T), in which it performs adaptive and consistent multi-view representation learning through two benchmark graphs. Specifically, we construct benchmark graphs via semantic dependency parsing of MWP text, considering both semantic and quantitative aspects, i.e., semantic graph and quantitative graph. Then, the reconstruction strategy is employed to reconstruct the structure of the benchmark graphs to capture the adaptive representation information suitable for downstream tasks, while the alignment strategy is utilized to overcome the limitation of independent view representations by unifying the semantic and quantity embedding information through graph structure. Also, an adaptive length normalized loss balancing term for the tree-based decoder is introduced to control the model focus on label length during training, resulting in better equation generation. Extensive experiments demonstrate the effectiveness of the proposed approach on the MWP task. The empirical results show that MVG-DS-T achieves performance comparable to that of the state-of-the-art graph-based models in the existing literature.

中文翻译：

---

具有解决数学应用题双重策略的多视图图学习模型

最近，基于图的深度学习模型在生成数学应用题（MWP）的解决方案表达式方面表现出了卓越的性能。然而，这些模型大多数都没有考虑到构建先验知识图的局限性和错误，这可能会影响其在实际应用中的准确性和可靠性。此外，在图学习过程中，他们专注于从每个给定的图中提取信息，而忽略了图表示学习的适应性和统一性。在本文中，我们提出了一种新颖的双策略多视图图学习树模型（MVG-DS-T），其中它通过两个基准图执行自适应且一致的多视图表示学习。具体来说，我们通过MWP文本的语义依赖解析构建基准图，同时考虑语义和定量方面，即语义图和定量图。然后，采用重建策略重建基准图的结构，以捕获适合下游任务的自适应表示信息，同时利用对齐策略通过图统一语义和数量嵌入信息来克服独立视图表示的限制。结构。此外，引入了基于树的解码器的自适应长度归一化损失平衡项，以控制模型在训练期间关注标签长度，从而产生更好的方程。大量实验证明了所提出的方法在 MWP 任务上的有效性。实证结果表明，MVG-DS-T 的性能可与现有文献中最先进的基于图的模型相媲美。