Unsupervised Multiple Choices Question Answering: Start Learning from Basic Knowledge
This work addresses the problem of reducing annotation costs for question-answering systems, though it is incremental as it builds on existing unsupervised techniques.
The paper tackles unsupervised multiple-choice question answering by using noisy probability estimates of correct choices as training guidance, achieving results that outperform baseline methods on RACE and are comparable to some supervised approaches on MC500.
In this paper, we study the possibility of almost unsupervised Multiple Choices Question Answering (MCQA). Starting from very basic knowledge, MCQA model knows that some choices have higher probabilities of being correct than the others. The information, though very noisy, guides the training of an MCQA model. The proposed method is shown to outperform the baseline approaches on RACE and even comparable with some supervised learning approaches on MC500.