Tree-structured Decoding for Solving Math Word Problems

Automatically solving math word problems is an interesting research topic that needs to bridge natural language descriptions and formal math equations. Previous studies introduced end-to-end neural network methods, but these approaches did not efficiently consider an important characteristic of the equation, i.e., an abstract syntax tree. To address this problem, we propose a tree-structured decoding method that generates the abstract syntax tree of the equation in a top-down manner. In addition, our approach can automatically stop during decoding without a redundant stop token. The experimental results show that our method achieves single model state-of-the-art performance on Math23K, which is the largest dataset on this task.

[1]  Heng Tao Shen,et al.  Template-Based Math Word Problem Solvers with Recursive Neural Networks , 2019, AAAI.

[2]  Oren Etzioni,et al.  Learning to Solve Arithmetic Word Problems with Verb Categorization , 2014, EMNLP.

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

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

[5]  Ming-Wei Chang,et al.  Annotating Derivations: A New Evaluation Strategy and Dataset for Algebra Word Problems , 2016, EACL.

[6]  Tommi S. Jaakkola,et al.  Tree-structured decoding with doubly-recurrent neural networks , 2016, ICLR.

[7]  Anirban Mukherjee,et al.  A review of methods for automatic understanding of natural language mathematical problems , 2008, Artificial Intelligence Review.

[8]  Wei-Ying Ma,et al.  How well do Computers Solve Math Word Problems? Large-Scale Dataset Construction and Evaluation , 2016, ACL.

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

[10]  Yun-Nung Chen,et al.  Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems , 2018, NAACL.

[11]  Liang Lu,et al.  Top-down Tree Long Short-Term Memory Networks , 2015, NAACL.

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

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

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

[15]  Lili Mou,et al.  A Grammar-Based Structural CNN Decoder for Code Generation , 2018, AAAI.

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

[17]  Heng Tao Shen,et al.  MathDQN: Solving Arithmetic Word Problems via Deep Reinforcement Learning , 2018, AAAI.

[18]  Mirella Lapata,et al.  Language to Logical Form with Neural Attention , 2016, ACL.

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

[20]  Dan Roth,et al.  Solving General Arithmetic Word Problems , 2016, EMNLP.

[21]  Oren Etzioni,et al.  Parsing Algebraic Word Problems into Equations , 2015, TACL.

[22]  Dan Klein,et al.  Abstract Syntax Networks for Code Generation and Semantic Parsing , 2017, ACL.