Event correlation reasoning infers whether a natural language paragraph containing multiple events conforms to human common sense. For example, "Andrew was very drowsy, so he took a long nap, and now he is very alert" is sound and reasonable. In contrast, "Andrew was very drowsy, so he stayed up a long time, now he is very alert" does not comply with human common sense. Such reasoning capability is essential for many downstream tasks, such as script reasoning, abductive reasoning, narrative incoherence, story cloze test, etc. However, conducting event correlation reasoning is challenging due to a lack of large amounts of diverse event-based knowledge and difficulty in capturing correlation among multiple events. In this paper, we propose EventBERT, a pre-trained model to encapsulate eventuality knowledge from unlabeled text. Specifically, we collect a large volume of training examples by identifying natural language paragraphs that describe multiple correlated events and further extracting event spans in an unsupervised manner. We then propose three novel event- and correlation-based learning objectives to pre-train an event correlation model on our created training corpus. Empirical results show EventBERT outperforms strong baselines on four downstream tasks, and achieves SoTA results on most of them. Besides, it outperforms existing pre-trained models by a large margin, e.g., 6.5~23%, in zero-shot learning of these tasks.
翻译:事件相关推理推算包含多个事件的自然语言段落是否符合人类常识。 例如, “ Andrew ” ( Andrew ) 是一个包含多个事件的自然语言段落是否与人类常识相符的自然语言段落。 例如, “ Andrew ” ( Andrew ) 是一个非常沉睡, 所以他睡了很久, 现在非常警觉 ” 是合理和合理的。 相反, “ Andrew ” ( Andrew ) 是一个非常沉睡, 所以他保持了很长的时间, 所以他非常警觉 ” 不符合人类常识。 这种推理能力对于许多下游任务至关重要, 如脚本推理、 绑架推理、 叙事不连贯、 故事凝聚测试等。 但是, 进行事件相关推理具有挑战性, 原因是缺乏大量基于事件的知识, 并且难以捕捉到多个事件之间的关联性。 在本文中,我们提议“ DEBERT” ( EDBERT) (Empicalal ) 模式中, 最先行的模型显示一个大型的“ REdustrublegal Ex Ex leblegleal lady ” (I) ) 。 任务, 。