Textual Enhanced Contrastive Learning for Solving Math Word Problems
Textual Enhanced Contrastive Learning for Solving Math Word Problems
复制标题
DOI：
10.48550/arxiv.2211.16022
复制
发表时间：
2022-11
期刊：
影响因子：
3.9
通讯作者：
Yibin Shen;Qianying Liu;Zhuoyuan Mao;Fei Cheng;S. Kurohashi
中科院分区：
文献类型：
--
作者：
Yibin Shen;Qianying Liu;Zhuoyuan Mao;Fei Cheng;S. Kurohashi
解决数学字题是一项分析数量关系的任务，需要对上下文自然语言信息有准确的理解。最近的研究表明，目前的模型依赖于浅层启发式来预测解决方案，并且很容易被小的文本扰动所误导。为了解决这个问题，我们提出了一个文本增强对比学习框架，该框架强制模型区分语义相似的示例，同时持有不同的数学逻辑。我们采用自监督方式策略，通过文本重新排序或问题重构来丰富具有细微文本差异的示例。然后，我们从方程和文本的角度检索最难区分的样本，并指导模型学习它们的表示。实验结果表明，我们的方法在广泛使用的基准数据集和精心设计的中英文挑战数据集上都达到了最先进的水平。我们的代码和数据可在\url{https://github.com/yiyunya/Textual_CL_MWP}获得
Solving math word problems is the task that analyses the relation of quantities and requires an accurate understanding of contextual natural language information. Recent studies show that current models rely on shallow heuristics to predict solutions and could be easily misled by small textual perturbations. To address this problem, we propose a Textual Enhanced Contrastive Learning framework, which enforces the models to distinguish semantically similar examples while holding different mathematical logic. We adopt a self-supervised manner strategy to enrich examples with subtle textual variance by textual reordering or problem re-construction. We then retrieve the hardest to differentiate samples from both equation and textual perspectives and guide the model to learn their representations. Experimental results show that our method achieves state-of-the-art on both widely used benchmark datasets and also exquisitely designed challenge datasets in English and Chinese. \footnote{Our code and data is available at \url{https://github.com/yiyunya/Textual_CL_MWP}