论文标题
对教育的回答不足问题的可行性研究
A Feasibility Study of Answer-Agnostic Question Generation for Education
论文作者
论文摘要
我们对回答不可或缺的问题生成模型适用于教科书段落的适用性进行了可行性研究。我们表明，此类系统中的很大一部分错误是由于提出无关或不可解释的问题而引起的，并且可以通过提供汇总的输入来改善此类错误。我们发现，这些模型由专家注释者确定的，给出人写的摘要，而不是原始文本导致生成问题的可接受性（33％$ \ rightarrow $ 83％）的大幅提高。我们还发现，在没有人写的摘要的情况下，自动摘要可以作为良好的中间立场。
We conduct a feasibility study into the applicability of answer-agnostic question generation models to textbook passages. We show that a significant portion of errors in such systems arise from asking irrelevant or uninterpretable questions and that such errors can be ameliorated by providing summarized input. We find that giving these models human-written summaries instead of the original text results in a significant increase in acceptability of generated questions (33% $\rightarrow$ 83%) as determined by expert annotators. We also find that, in the absence of human-written summaries, automatic summarization can serve as a good middle ground.
