论文标题
文档级事件提取，并有效地端到端学习交叉事件依赖性
Document-level Event Extraction with Efficient End-to-end Learning of Cross-event Dependencies
论文作者
论文摘要
完全理解叙事通常需要在整个文档的背景下识别事件并对事件关系进行建模。但是，文档级事件提取是一项具有挑战性的任务，因为它需要提取事件和实体核心，并捕获跨越不同句子的参数。现有关于事件提取的作品通常局限于从单个句子中提取事件，这些句子未能捕获事件之间的关系，该事件是在文档的规模上提到的，以及与事件触发器不同句子中出现的事件参数。在本文中，我们提出了一个端到端模型，利用了一个结构化的预测算法，以有效地捕获文档级别事件提取的跨事物依赖关系。实验结果表明，我们的方法与ACE05上的基于CRF的模型相当，而计算效率则明显更高。
Fully understanding narratives often requires identifying events in the context of whole documents and modeling the event relations. However, document-level event extraction is a challenging task as it requires the extraction of event and entity coreference, and capturing arguments that span across different sentences. Existing works on event extraction usually confine on extracting events from single sentences, which fail to capture the relationships between the event mentions at the scale of a document, as well as the event arguments that appear in a different sentence than the event trigger. In this paper, we propose an end-to-end model leveraging Deep Value Networks (DVN), a structured prediction algorithm, to efficiently capture cross-event dependencies for document-level event extraction. Experimental results show that our approach achieves comparable performance to CRF-based models on ACE05, while enjoys significantly higher computational efficiency.
