SkillQG：学习生成用于阅读理解评估的问题
SkillQG: Learning to Generate Question for Reading Comprehension Assessment
AI总结：
SkillQG提出了一种基于技能条件的问题生成框架，通过分层技能模式界定理解类型并增强输入，实现可控生成，在质量、相关性和技能可控性上优于基线，并提升下游问答性能。
摘要：
我们提出了SkillQG：一个具有可控理解类型的问题生成框架，用于评估和改进机器阅读理解模型。现有问题生成系统广泛地通过字面信息（如疑问词和答案类型）来区分问题，从而为给定上下文生成语义相关的问题。然而，它们很少考虑问题的理解本质，即不同问题所体现的不同理解能力。相比之下，我们的SkillQG能够针对基于其构建的问答模型的能力进行细粒度的评估和改进。具体来说，我们首先基于一个分层技能模式来界定问题的理解类型，然后将SkillQG构建为技能条件的问题生成器。此外，为了提高生成的可控性，我们用问题焦点和技能特定知识来增强输入文本，这些是通过迭代提示预训练语言模型构建的。实证结果表明，SkillQG在质量、相关性和技能可控性方面优于基线，同时在下游问答任务中显示出有前景的性能提升。
英文摘要：
We present $\textbf{$\texttt{SkillQG}$}$: a question generation framework with controllable comprehension types for assessing and improving machine reading comprehension models. Existing question generation systems widely differentiate questions by $\textit{literal}$ information such as question words and answer types to generate semantically relevant questions for a given context. However, they rarely consider the $\textit{comprehension}$ nature of questions, i.e. the different comprehension capabilities embodied by different questions. In comparison, our $\texttt{SkillQG}$ is able to tailor a fine-grained assessment and improvement to the capabilities of question answering models built on it. Specifically, we first frame the comprehension type of questions based on a hierarchical skill-based schema, then formulate $\texttt{SkillQG}$ as a skill-conditioned question generator. Furthermore, to improve the controllability of generation, we augment the input text with question focus and skill-specific knowledge, which are constructed by iteratively prompting the pre-trained language models. Empirical results demonstrate that $\texttt{SkillQG}$ outperforms baselines in terms of quality, relevance, and skill-controllability while showing a promising performance boost in downstream question answering task.
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。
