论文标题
通过回答（几乎）自然问题提取事件
Event Extraction by Answering (Almost) Natural Questions
论文作者
论文摘要
事件提取的问题需要检测事件触发器并提取其相应的参数。事件参数提取中的现有工作通常在很大程度上依赖于实体识别作为预处理/并发步骤，从而导致众所周知的错误传播问题。为了避免此问题，我们通过将其作为问题回答（QA）任务提出的新范式提取事件提取，该任务以端到端的方式提取事件参数。经验结果表明，我们的框架大大优于先验方法。此外，它也能够提取事件参数，以了解在训练时间（零射击学习设置）中看不见的角色。
The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments. Existing work in event argument extraction typically relies heavily on entity recognition as a preprocessing/concurrent step, causing the well-known problem of error propagation. To avoid this issue, we introduce a new paradigm for event extraction by formulating it as a question answering (QA) task that extracts the event arguments in an end-to-end manner. Empirical results demonstrate that our framework outperforms prior methods substantially; in addition, it is capable of extracting event arguments for roles not seen at training time (zero-shot learning setting).
