arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.12898cs.CLcs.AIcs.CYcs.IRcs.LG
收藏

为测验生成候选答案和测试感知问题生成器

Generating Answer Candidates for Quizzes and Answer-Aware Question Generators

Sofia University(索非亚大学);University of Cambridge(剑桥大学);Releva AI

Kristiyan Vachev, Momchil Hardalov, Georgi Karadzhov, Georgi Georgiev, Ivan Koychev, Preslav Nakov

摘要:

在教育方面,开放式测验问题已成为评估学生知识的重要工具。然而,手动准备这样的问题是一项繁琐的任务,因此自动问题生成已被提出作为一种可能的替代方案。到目前为止,绝大多数研究都集中在生成问题文本上,依赖于具有现成答案的问答数据集,而如何首先提出答案候选人的问题在很大程度上被忽视了。在这里,我们的目标是弥合这一差距。特别是,我们提出了一个模型,可以生成一个指定数量的答案候选人为一个给定的文本通道,然后可以使用教师手动写问题,或可以作为输入传递到自动答案感知问题生成器。我们的实验表明,我们提出的答案候选生成模型优于几个基线。

英文摘要:

In education, open-ended quiz questions have become an important tool for assessing the knowledge of students. Yet, manually preparing such questions is a tedious task, and thus automatic question generation has been proposed as a possible alternative. So far, the vast majority of research has focused on generating the question text, relying on question answering datasets with readily picked answers, and the problem of how to come up with answer candidates in the first place has been largely ignored. Here, we aim to bridge this gap. In particular, we propose a model that can generate a specified number of answer candidates for a given passage of text, which can then be used by instructors to write questions manually or can be passed as an input to automatic answer-aware question generators. Our experiments show that our proposed answer candidate generation model outperforms several baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑