Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems

TL;DR

This paper introduces a method for solving algebraic word problems by generating natural language rationales that guide the induction of arithmetic programs, using a large dataset to demonstrate effectiveness.

Contribution

It proposes a novel approach of using answer rationales as intermediate supervision to induce arithmetic programs for algebraic problems.

Findings

Generated rationales improve program induction accuracy

Large dataset of 100,000 questions and rationales supports training

Indirect supervision via rationales is effective for learning arithmetic programs

Abstract

Solving algebraic word problems requires executing a series of arithmetic operations---a program---to obtain a final answer. However, since programs can be arbitrarily complicated, inducing them directly from question-answer pairs is a formidable challenge. To make this task more feasible, we solve these problems by generating answer rationales, sequences of natural language and human-readable mathematical expressions that derive the final answer through a series of small steps. Although rationales do not explicitly specify programs, they provide a scaffolding for their structure via intermediate milestones. To evaluate our approach, we have created a new 100,000-sample dataset of questions, answers and rationales. Experimental results show that indirect supervision of program learning via answer rationales is a promising strategy for inducing arithmetic programs.