應用自動資訊擷取於故事書問答生成之研究

Applying Information Extraction to Storybook Question and Answer Generation

從故事文本中產生高品質且通順的問題—答案配對是一件耗時且耗力的事情，問題的生成目的不是要讓學生回答不出來，而是幫助學生了解故事所要傳達的訊息，因此需要經過巧妙的設計將文本中的重要資訊當成答案，並且生成與之相對應的問題。在本文中，我們通過將問題類型及其類型定義結合到輸入中來改進Fairy-TaleQA問題生成方法，以微調BART(Lewis et al., 2020)模型改進問題生成效能。此外，我們進一步利用(Zhong andChen, 2021)中的實體和關係提取作為基於模板的問題生成的元素。使用pipeline的方法(Zhong and Chen, 2021)，最後將擷取出來的關係作為模板式生成的要素。

For educators, how to generate high quality question-answer pairs from story text is a time-consuming and labor-intensive task. The purpose is not to make students unable to answer, but to ensure that students understand the story text through the generated question-answer pairs. In this paper, we improve the FairyTaleQA question generation method by incorporating question type and its definition to the input for fine-tuning the BART (Lewis et al., 2020) model. Furthermore, we make use of the entity and relation extraction from (Zhong and Chen, 2021) as an element of templatebased question generation.