论文标题
问题类型驱动和复制损失增强的框架，用于答案 - 不合时宜的神经问题生成
A Question Type Driven and Copy Loss Enhanced Frameworkfor Answer-Agnostic Neural Question Generation
论文作者
论文摘要
答案不足的问题生成是一项重大且具有挑战性的任务，旨在自动为给定句子生成问题，但没有答案。在本文中，我们提出了两种新策略来处理此任务：问题类型预测和复制损失机制。问题类型模块是预测应提出的问题的类型，这使我们的模型可以为同一源句子生成多种类型的问题。新副本损失增强了原始复制机制，以确保在产生问题时复制源句中的每个重要单词。我们的集成模型的表现优于答案不足问题的最新方法，在小队上的BLEU-4分数为13.9。人类评估进一步验证了我们生成的问题的高质量。我们将使我们的代码公开用于进一步研究。
The answer-agnostic question generation is a significant and challenging task, which aims to automatically generate questions for a given sentence but without an answer. In this paper, we propose two new strategies to deal with this task: question type prediction and copy loss mechanism. The question type module is to predict the types of questions that should be asked, which allows our model to generate multiple types of questions for the same source sentence. The new copy loss enhances the original copy mechanism to make sure that every important word in the source sentence has been copied when generating questions. Our integrated model outperforms the state-of-the-art approach in answer-agnostic question generation, achieving a BLEU-4 score of 13.9 on SQuAD. Human evaluation further validates the high quality of our generated questions. We will make our code public available for further research.
