In this paper, we propose a recent and under-researched paradigm for the task of event detection (ED) by casting it as a question-answering (QA) problem with the possibility of multiple answers and the support of entities. The extraction of event triggers is, thus, transformed into the task of identifying answer spans from a context, while also focusing on the surrounding entities. The architecture is based on a pre-trained and fine-tuned language model, where the input context is augmented with entities marked at different levels, their positions, their types, and, finally, the argument roles. Experiments on the ACE~2005 corpus demonstrate that the proposed paradigm is a viable solution for the ED task and it significantly outperforms the state-of-the-art models. Moreover, we prove that our methods are also able to extract unseen event types.
翻译:在本文中,我们提出了一个最近和研究不足的发现事件(ED)任务的模式,将它作为一个问题解答(QA)问题,提出多个答案和实体支持的可能性。因此,从事件触发器的抽取转化成从一个背景中找出答案的任务,同时也侧重于周围实体。这个结构基于预先培训和微调的语言模式,在这个模式中,输入环境由不同层次的实体、其位置、类型以及最后的争论作用得到加强。关于ACE-2005的实验表明,拟议的模式是ED任务的可行解决办法,大大超越了最先进的模式。此外,我们证明我们的方法也能够提取出不可见事件的类型。