Learning from Explicit and Implicit Supervision Jointly for Algebra Word Problems
Published in EMNLP-2016, 2016
Automatically solving algebra word problems has raised considerable interest recently. Existing state-of-the-art approaches mainly rely on learning from human annotated equations. In this paper, we demonstrate that it is possible to efficiently mine algebra problems and their numerical solutions with little to no manual effort. To leverage the mined dataset, we propose a novel structured-output learning algorithm that aims to learn from both explicit (e.g., equations) and implicit (e.g., solutions) supervision signals jointly. Enabled by this new algorithm, our model gains 4.6% absolute improvement in accuracy on the ALG514 benchmark compared to the one without using implicit supervision. The final model also outperforms the current state-of-the-art approach by 3%.