论文标题
高级文本理解的好奇问题生成
Inquisitive Question Generation for High Level Text Comprehension
论文作者
论文摘要
在各种环境中，人类自然而然地出现了好奇的探测问题，但对于自动系统来说是一项艰巨的任务。一种自然类型的问题要试图在文本理解过程中填补知识的空白，例如阅读新闻文章：我们可能会询问背景信息，发生的事情背后的更深层次的原因或更多内容。尽管数据驱动的方法最近取得了进展，但产生此类问题的范围超出了在现有数据集中训练的模型范围。 我们介绍了好奇心，这是一个〜19K问题的数据集，这些问题是在一个人通过文档阅读时引起的。与现有数据集相比，好奇的问题更多地针对文本的高级（语义和话语）理解。我们表明读者参与了一系列务实的策略来寻求信息。最后，我们评估了基于GPT-2的问题生成模型，并表明我们的模型能够产生合理的问题，尽管该任务具有挑战性，并强调了上下文对产生好奇问题的重要性。
Inquisitive probing questions come naturally to humans in a variety of settings, but is a challenging task for automatic systems. One natural type of question to ask tries to fill a gap in knowledge during text comprehension, like reading a news article: we might ask about background information, deeper reasons behind things occurring, or more. Despite recent progress with data-driven approaches, generating such questions is beyond the range of models trained on existing datasets. We introduce INQUISITIVE, a dataset of ~19K questions that are elicited while a person is reading through a document. Compared to existing datasets, INQUISITIVE questions target more towards high-level (semantic and discourse) comprehension of text. We show that readers engage in a series of pragmatic strategies to seek information. Finally, we evaluate question generation models based on GPT-2 and show that our model is able to generate reasonable questions although the task is challenging, and highlight the importance of context to generate INQUISITIVE questions.
