Commonsense reasoning, aiming at endowing machines with a human-like ability to make situational presumptions, is extremely challenging to generalize. For someone who barely knows about "meditation," while is knowledgeable about "singing," he can still infer that "meditation makes people relaxed" from the existing knowledge that "singing makes people relaxed" by first conceptualizing "singing" as a "relaxing event" and then instantiating that event to "meditation." This process, known as conceptual induction and deduction, is fundamental to commonsense reasoning while lacking both labeled data and methodologies to enhance commonsense modeling. To fill such a research gap, we propose CAT (Contextualized ConceptuAlization and InsTantiation), a semi-supervised learning framework that integrates event conceptualization and instantiation to conceptualize commonsense knowledge bases at scale. Extensive experiments show that our framework achieves state-of-the-art performances on two conceptualization tasks, and the acquired abstract commonsense knowledge can significantly improve commonsense inference modeling. Our code, data, and fine-tuned models are publicly available at https://github.com/HKUST-KnowComp/CAT.

翻译：常识推理旨在赋予机器类人的情境假设能力，其泛化极具挑战性。对于一个几乎不了解"冥想"但熟悉"唱歌"的人而言，他仍能从"唱歌使人放松"这一现有知识推断出"冥想使人放松"，其过程首先将"唱歌"概念化为"放松事件"，然后将该事件实例化为"冥想"。这一概念归纳与演绎的过程是常识推理的基础，但目前缺乏标注数据及增强常识建模的方法。为填补这一研究空白，我们提出CAT（语境化概念化与实例化）框架——一种半监督学习框架，通过整合事件概念化与实例化，实现常识知识库的大规模概念化。大量实验表明，该框架在两个概念化任务上均达到最先进水平，且获取的抽象常识知识能显著提升常识推理建模能力。我们的代码、数据及微调模型已在https://github.com/HKUST-KnowComp/CAT公开。