Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems
This addresses the problem of solving complex algebraic word problems for AI systems, but it is incremental as it builds on existing program induction methods.
The paper tackled the challenge of inducing arithmetic programs from algebraic word problems by generating answer rationales as intermediate steps, and created a 100,000-sample dataset to evaluate this approach, showing it as a promising strategy for program learning.
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.