Semantically-Aligned Equation Generation for Solving and Reasoning Math Word Problems

Solving math word problems is a challenging task that requires accurate natural language understanding to bridge natural language texts and math expressions. Motivated by the intuition about how human generates the equations given the problem texts, this paper presents a neural approach to automatically solve math word problems by operating symbols according to their semantic meanings in texts. This paper views the process of generating equation as a bridge between the semantic world and the symbolic world, where the proposed neural math solver is based on an encoder-decoder framework. In the proposed model, the encoder is designed to understand the semantics of problems, and the decoder focuses on tracking semantic meanings of the generated symbols and then deciding which symbol to generate next. The preliminary experiments are conducted in a dataset Math23K, and our model significantly outperforms both the state-of-the-art single model and the best non-retrieval-based model over about 10% accuracy, demonstrating the effectiveness of bridging the symbolic and semantic worlds from math word problems.

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

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

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

[4]  Sudip Kumar Naskar,et al.  Solving Arithmetic Mathematical Word Problems: A Review and Recent Advancements , 2017, ICITAM.

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

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

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

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

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

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

[11]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[12]  Matthijs Douze,et al.  FastText.zip: Compressing text classification models , 2016, ArXiv.

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

[14]  Dan Roth,et al.  Equation Parsing : Mapping Sentences to Grounded Equations , 2016, EMNLP.

[15]  Alex Graves,et al.  Neural Turing Machines , 2014, ArXiv.

[16]  Dan Roth,et al.  Reasoning about Quantities in Natural Language , 2015, TACL.

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

[18]  Ming-Wei Chang,et al.  Learning from Explicit and Implicit Supervision Jointly For Algebra Word Problems , 2016, EMNLP.

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

[20]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[21]  Dipti Misra Sharma,et al.  Deep Neural Network based system for solving Arithmetic Word problems , 2017, IJCNLP.

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

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