弱监督、具有可解释性的应用题解答

AITIME论道

于 2021-04-25 17:30:06 发布

阅读量506

点赞数 1

文章标签：神经网络大数据编程语言 python 机器学习

本文链接：https://blog.csdn.net/AITIME_HY/article/details/116141826

版权

本文介绍两种AI解数学题的方法，一种是基于弱监督的学习方法——Learning by Fixing，该方法仅需最终答案，通过符号执行和修正机制生成多种解决方案。另一种是SMART，引入情境模型，利用属性文法解析应用题，提供解题过程的可解释性。实验表明，这两种方法在多样化解题和可解释性上优于传统神经网络模型。

摘要由CSDN通过智能技术生成

点击蓝字

关注我们

AI TIME欢迎每一位AI爱好者的加入！

Previous neural solvers of math word problems (MWPs) are learned with full supervision and fail to generate diverse solutions. In this paper, we address this issue by introducing a weakly-supervised paradigm for learning MWPs. Our method only requires the annotations of the final answers and can generate various solutions for a single problem. To boost weakly-supervised learning, we propose a novel learning-by-fixing (LBF) framework, which corrects the misperceptions of the neural network via symbolic reasoning. Specifically, for an incorrect solution tree generated by the neural network, the fixing mechanism propagates the error from the root node to the leaf nodes and infers the most probable fix that can be executed to get the desired answer. To generate more diverse solutions, tree regularization is applied to guide the efficient shrinkage and exploration of the solution space, and a memory buffer is designed to track and save the discovered various fixes for each problem.

Previous neural solvers of math word problems directly translate problem texts into equations, lacking an explicit interpretation of the situations, and often fail to handle more sophisticated situations. To address such limits of neural solvers, we introduce the concept of a situation model, which originates from psychology studies to represent the mental states of humans in problem-solving, and propose SMART, which adopts attributed grammar as the representation of situation models for algebra story problems. Specifically, we first train an information extraction module to extract nodes, attributes, and relations from problem texts and then generate a parse graph based on a pre-defined attributed grammar. An iterative learning strategy is also proposed to improve the performance of SMART further.