A Goal-Driven Tree-Structured Neural Model for Math Word Problems

Most existing neural models for math word problems exploit Seq2Seq model to generate solution expressions sequentially from left to right, whose results are far from satisfactory due to the lack of goal-driven mechanism commonly seen in human problem solving. This paper proposes a treestructured neural model to generate expression tree in a goal-driven manner. Given a math word problem, the model first identifies and encodes its goal to achieve, and then the goal gets decomposed into sub-goals combined by an operator in a top-down recursive way. The whole process is repeated until the goal is simple enough to be realized by a known quantity as leaf node. During the process, two-layer gated-feedforward networks are designed to implement each step of goal decomposition, and a recursive neural network is used to encode fulfilled subtrees into subtree embeddings, which provides a better representation of subtrees than the simple goals of subtrees. Experimental results on the dataset Math23K have shown that our treestructured model outperforms significantly several state-of-the-art models.

[1]  Shuming Shi,et al.  Learning Fine-Grained Expressions to Solve Math Word Problems , 2017, EMNLP.

[2]  Hannaneh Hajishirzi,et al.  Data-Driven Methods for Solving Algebra Word Problems , 2018, ArXiv.

[3]  Dan Roth,et al.  Unit Dependency Graph and Its Application to Arithmetic Word Problem Solving , 2016, AAAI.

[4]  Shuming Shi,et al.  Deep Neural Solver for Math Word Problems , 2017, EMNLP.

[5]  Wang Ling,et al.  Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems , 2017, ACL.

[6]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[7]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[8]  Carl Vogel,et al.  Proceedings of the 16th International Conference on Computational Linguistics , 1996, COLING 1996.

[9]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[10]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[11]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[12]  Yan Wang,et al.  Translating a Math Word Problem to a Expression Tree , 2018, EMNLP.

[13]  Lipu Zhou,et al.  Learn to Solve Algebra Word Problems Using Quadratic Programming , 2015, EMNLP.

[14]  Yefim Bakman,et al.  Robust Understanding of Word Problems with Extraneous Information , 2007, math/0701393.

[15]  Noah A. Smith,et al.  Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , 2016, ACL 2016.

[16]  Dan Roth,et al.  Mapping to Declarative Knowledge for Word Problem Solving , 2017, TACL.

[17]  Luke S. Zettlemoyer,et al.  Learning to Automatically Solve Algebra Word Problems , 2014, ACL.

[18]  Shuming Shi,et al.  Automatically Solving Number Word Problems by Semantic Parsing and Reasoning , 2015, EMNLP.

[19]  Ren Yun,et al.  Frame-Based Calculus of Solving Arithmetic Multi-Step Addition and Subtraction Word Problems , 2010, 2010 Second International Workshop on Education Technology and Computer Science.

[20]  Jing Liu,et al.  Neural Math Word Problem Solver with Reinforcement Learning , 2018, COLING.

[21]  Heng Tao Shen,et al.  The Gap of Semantic Parsing: A Survey on Automatic Math Word Problem Solvers , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Roman Grundkiewicz,et al.  Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing , 2015, EMNLP 2015.