Event-centric structured prediction involves predicting structured outputs of events. In most NLP cases, event structures are complex with manifold dependency, and it is challenging to effectively represent these complicated structured events. To address these issues, we propose Structured Prediction with Energy-based Event-Centric Hyperspheres (SPEECH). SPEECH models complex dependency among event structured components with energy-based modeling, and represents event classes with simple but effective hyperspheres. Experiments on two unified-annotated event datasets indicate that SPEECH is predominant in event detection and event-relation extraction tasks.

翻译：以事件为中心的结构化预测涉及预测事件的结构化输出。在大多数自然语言处理案例中，事件结构复杂且具有多重依赖关系，有效表征这些复杂结构化事件具有挑战性。为解决这些问题，我们提出基于能量的以事件为中心超球面结构化预测方法（SPEECH）。该方法通过能量建模对事件结构化组件间的复杂依赖关系进行建模，并采用简洁而有效的超球面来表征事件类别。在两个统一标注事件数据集上的实验表明，SPEECH在事件检测与事件关系抽取任务中表现优异。