Learning to Automatically Solve Algebra Word Problems
Author(s)Kushman, Nate; Artzi, Yoav; Zettlemoyer, Luke; Barzilay, Regina
MetadataShow full item record
We present an approach for automatically learning to solve algebra word problems. Our algorithm reasons across sentence boundaries to construct and solve a system of linear equations, while simultaneously recovering an alignment of the variables and numbers in these equations to the problem text. The learning algorithm uses varied supervision, including either full equations or just the final answers. We evaluate performance on a newly gathered corpus of algebra word problems, demonstrating that the system can correctly answer almost 70% of the questions in the dataset. This is, to our knowledge, the first learning result for this task.
DepartmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics
Association for Computational Linguistics
Kushman, Nate, Yoav Artzi, Luke Zettlemoyer, and Regina Barzilay. "Learning to Automatically Solve Algebra Word Problems." 52nd Annual Meeting of the Association for Computational Linguistics (June 2014).
Author's final manuscript