论文标题
类似的数学单词问题通过增强的问题解决关联解决
Analogical Math Word Problems Solving with Enhanced Problem-Solution Association
论文作者
论文摘要
数学单词问题（MWP）求解是有关回答需要类似人类推理能力的重要任务。类似推理长期以来一直在数学教育中使用，因为它使学生能够应用数学情况的共同关系结构来解决新问题。在本文中，我们建议通过利用类似MWP来构建一种新颖的MWP求解器，从而提高求解器在不同类型的MWP上的概括能力。称为类比识别的关键思想是将类似的MWP对在潜在空间中关联，即，在远离非Analogical的MWP时，将MWP编码靠近另一个类似MWP。此外，将解决方案鉴别器集成到MWP求解器中，以增强MWPS的表示与其真实解决方案之间的关联。评估结果证明，我们提出的类似学习策略促进了MWP-bert在MATH23K上的MATH23K上的性能，在最新模型生成2Rank上，编码器中的参数较少5倍。我们还发现，由于来自简单的MWP的类比学习，我们的模型在解决难以解决的MWP方面具有更强的泛化能力。
Math word problem (MWP) solving is an important task in question answering which requires human-like reasoning ability. Analogical reasoning has long been used in mathematical education, as it enables students to apply common relational structures of mathematical situations to solve new problems. In this paper, we propose to build a novel MWP solver by leveraging analogical MWPs, which advance the solver's generalization ability across different kinds of MWPs. The key idea, named analogy identification, is to associate the analogical MWP pairs in a latent space, i.e., encoding an MWP close to another analogical MWP, while moving away from the non-analogical ones. Moreover, a solution discriminator is integrated into the MWP solver to enhance the association between the representations of MWPs and their true solutions. The evaluation results verify that our proposed analogical learning strategy promotes the performance of MWP-BERT on Math23k over the state-of-the-art model Generate2Rank, with 5 times fewer parameters in the encoder. We also find that our model has a stronger generalization ability in solving difficult MWPs due to the analogical learning from easy MWPs.
