[2A2] [General Session] 2. Machine Learning

[2A2-05] Solving Four Arithmetic Operation Problems and Word Algebra Problems by Neural Programmer-Interpreters

〇Shota Katsumata¹, Katsumi Inoue^1,2 (1. Tokyo Institute of Technology, 2. National Institute of Informatics)

Keywords:Neural Programmer-Interpreters, Deep Learning, Programming by Example, Inductive Programming, Representation Leaning

In this paper we extend the arithmetic operations of the Neural Programmer-Interpreters (NPI). NPI is a recurrent and compositional neural network that learns to represent and execute programs. First, we enable NPI to execute not only the addition that NPI was originally possible but also the other three arithmetic operations, i.e. subtraction, multiplication and division. Then, we extended NPI to make it possible to share subprograms between tasks for improving learning efficiency. Next, we solve word algebra problems for elementary school-level mathematics which can be solved by using four arithmetic operations. For this purpose, we develop a converter that converts word algebra problems into mathematical expressions. This neural network is based on the Sequence-to-Sequence model with the attention mechanism. Using this neural network and NPI, we solve the data sets of word algebra problems and show that the accuracy of our method is better than the other existing methods.