EquGener: A Reasoning Network for Word Problem Solving by Generating Arithmetic Equations

Word problem solving has always been a challenging task as it involves reasoning across sentences, identification of operations and their order of application on relevant operands. Most of the earlier systems attempted to solve word problems with tailored features for handling each category of problems. In this paper, we present a new approach to solve simple arithmetic problems. Through this work we introduce a novel method where we first learn a dense representation of the problem description conditioned on the question in hand. We leverage this representation to generate the operands and operators in the appropriate order. Our approach improves upon the state-of-the-art system by 3% in one benchmark dataset while ensuring comparable accuracies in other datasets.

[1]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

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

[3]  Jason Weston,et al.  Memory Networks , 2014, ICLR.

[4]  Keh-Yih Su,et al.  A Meaning-Based Statistical English Math Word Problem Solver , 2018, NAACL.

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

[6]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[7]  Jian Yin,et al.  Using Intermediate Representations to Solve Math Word Problems , 2018, ACL.

[8]  Steven Bird,et al.  NLTK: The Natural Language Toolkit , 2002, ACL.

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

[10]  Hannaneh Hajishirzi,et al.  MAWPS: A Math Word Problem Repository , 2016, NAACL.

[11]  Yoshua Bengio,et al.  Professor Forcing: A New Algorithm for Training Recurrent Networks , 2016, NIPS.

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

[13]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

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

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

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

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

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

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

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

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

[22]  Daniel G. Bobrow,et al.  A question-answering system for high school algebra word problems , 1899, AFIPS '64 (Fall, part I).

[23]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[24]  Jason Weston,et al.  End-To-End Memory Networks , 2015, NIPS.

[25]  Dan Roth,et al.  Illinois Math Solver: Math Reasoning on the Web , 2016, NAACL.

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

[27]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

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

[29]  Chitta Baral,et al.  Learning To Use Formulas To Solve Simple Arithmetic Problems , 2016, ACL.