Reverse Operation based Data Augmentation for Solving Math Word Problems

Automatically solving math word problems is a critical task in the field of natural language processing. Recent models have reached their performance bottleneck and require more high-quality data for training. Inspired by human double-checking mechanism, we propose a reverse operation based data augmentation method that makes use of mathematical logic to produce new high-quality math problems and introduce new knowledge points that can give supervision for new mathematical reasoning logic. We apply the augmented data on two SOTA math word problem solving models. Experimental results show the effectiveness of our approach\footnote{We will release our code and data after the paper is accepted.}.

[1]  Quoc V. Le,et al.  QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension , 2018, ICLR.

[2]  Gabriel Stanovsky,et al.  DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs , 2019, NAACL.

[3]  Ee-Peng Lim,et al.  Teacher-Student Networks with Multiple Decoders for Solving Math Word Problem , 2020, IJCAI.

[4]  Chitta Baral,et al.  VQA-LOL: Visual Question Answering under the Lens of Logic , 2020, ECCV.

[5]  Andy R. Terrel,et al.  SymPy: Symbolic computing in Python , 2017, PeerJ Prepr..

[6]  Bin Wang,et al.  An Improved Coarse-to-Fine Method for Solving Generation Tasks , 2019, ALTA.

[7]  Zhipeng Xie,et al.  A Goal-Driven Tree-Structured Neural Model for Math Word Problems , 2019, IJCAI.

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

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

[10]  Eugene Charniak,et al.  Computer Solution of Calculus Word Problems , 1969, IJCAI.

[11]  Daniel G. Bobrow,et al.  Natural Language Input for a Computer Problem Solving System , 1964 .

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

[13]  Hannaneh Hajishirzi,et al.  Logic-Guided Data Augmentation and Regularization for Consistent Question Answering , 2020, ACL.

[14]  Daisuke Kawahara,et al.  Tree-structured Decoding for Solving Math Word Problems , 2019, EMNLP.

[15]  Yan Wang,et al.  Graph-to-Tree Learning for Solving Math Word Problems , 2020, ACL.

[16]  Noah A. Smith,et al.  Question Generation via Overgenerating Transformations and Ranking , 2009 .

[17]  Kai Zou,et al.  EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks , 2019, EMNLP.

[18]  Yejin Choi,et al.  MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms , 2019, NAACL.

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

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

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

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

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

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

[25]  Dongyeop Kang,et al.  AdvEntuRe: Adversarial Training for Textual Entailment with Knowledge-Guided Examples , 2018, ACL.

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

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

[28]  Wei Lu,et al.  Text2Math: End-to-end Parsing Text into Math Expressions , 2019, EMNLP.

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