Learn to Solve Algebra Word Problems Using Quadratic Programming

This paper presents a new algorithm to automatically solve algebra word problems. Our algorithm solves a word problem via analyzing a hypothesis space containing all possible equation systems generated by assigning the numbers in the word problem into a set of equation system templates extracted from the training data. To obtain a robust decision surface, we train a log-linear model to make the margin between the correct assignments and the false ones as large as possible. This results in a quadratic programming (QP) problem which can be efficiently solved. Experimental results show that our algorithm achieves 79.7% accuracy, about 10% higher than the state-of-the-art baseline (Kushman et al., 2014).

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

[2]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

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

[4]  Roger Levy,et al.  Solving logic puzzles: From robust processing to precise semantics , 2004, Proceedings of the 2nd Workshop on Text Meaning and Interpretation - TextMean '04.

[5]  Hang Li.  Learning to Rank for Information Retrieval and Natural Language Processing , 2011, Synthesis Lectures on Human Language Technologies.

[6]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[7]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[8]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[9]  Hirokazu Anai,et al.  The Complexity of Math Problems - Linguistic, or Computational? , 2013, IJCNLP.

[10]  Ben Taskar,et al.  Learning structured prediction models: a large margin approach , 2005, ICML.

[11]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[13]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

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

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

[16]  Mark Steedman,et al.  Inducing Probabilistic CCG Grammars from Logical Form with Higher-Order Unification , 2010, EMNLP.

[17]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

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

[19]  Suma Bhat,et al.  Machine-guided Solution to Mathematical Word Problems , 2014, PACLIC.

[20]  Geoffrey Zweig,et al.  Linguistic Regularities in Continuous Space Word Representations , 2013, NAACL.