Event extraction involves the detection and extraction of both the event triggers and corresponding event arguments. Existing systems often decompose event extraction into multiple subtasks, without considering their possible interactions. In this paper, we propose EventGraph, a joint framework for event extraction, which encodes events as graphs. We represent event triggers and arguments as nodes in a semantic graph. Event extraction therefore becomes a graph parsing problem, which provides the following advantages: 1) performing event detection and argument extraction jointly; 2) detecting and extracting multiple events from a piece of text; and 3) capturing the complicated interaction between event arguments and triggers. Experimental results on ACE2005 show that our model is competitive to state-of-the-art systems and has substantially improved the results on argument extraction. Additionally, we create two new datasets from ACE2005 where we keep the entire text spans for event arguments, instead of just the head word(s). Our code and models are released as open-source.
翻译:事件提取包含事件触发器和相应事件参数的探测和提取。 现有的系统往往将事件提取分解成多个子任务, 而不考虑它们可能的相互作用 。 在本文中, 我们提出事件提取联合框架“ 事件 Grop ”, 将事件代码化为图表。 我们在语义图中代表事件触发器和参数作为节点。 因此, 事件提取成为一个图表解析问题, 提供了以下优点:(1) 共同执行事件检测和论证提取;(2) 从文本中探测和提取多个事件;(3) 捕捉事件参数和触发器之间的复杂互动。 ACE 2005 的实验结果显示, 我们的模型对最新工艺系统具有竞争力, 大大改进了参数提取的结果 。 此外, 我们从 ACE 2005 创建了两个新的数据集, 将整个文本用于事件论证, 而不是仅保留首字母 。 我们的代码和模型作为开放源发布 。