Identifying the Most Dominant Event in a News Article by Mining Event Coreference Relations
Identifying the Most Dominant Event in a News Article by Mining Event Coreference Relations
复制标题
DOI：
10.18653/v1/n18-2055
复制
发表时间：
2018-06
期刊：
影响因子：
--
通讯作者：
Prafulla Kumar Choubey;K. Raju;Ruihong Huang
中科院分区：
文献类型：
--
作者：
Prafulla Kumar Choubey;K. Raju;Ruihong Huang
识别文档中最主要和最中心的事件，它控制并连接文档中的其他前景和背景事件，对于许多应用都很有用，例如文本摘要，故事情节生成和文本分割。我们观察到，一个文档的中心事件通常有许多共指事件提及，分散在整个文档中，使子主题的平稳过渡。我们的实证实验，使用黄金事件共指关系，已经表明，一个文档的中心事件可以很好地识别挖掘属性的事件共指链。但是当切换到系统预测事件共指关系时，性能下降。此外，我们发现，中心事件可以更准确地确定进一步考虑的子事件的数量以及一个事件的真实状态。
Identifying the most dominant and central event of a document, which governs and connects other foreground and background events in the document, is useful for many applications, such as text summarization, storyline generation and text segmentation. We observed that the central event of a document usually has many coreferential event mentions that are scattered throughout the document for enabling a smooth transition of subtopics. Our empirical experiments, using gold event coreference relations, have shown that the central event of a document can be well identified by mining properties of event coreference chains. But the performance drops when switching to system predicted event coreference relations. In addition, we found that the central event can be more accurately identified by further considering the number of sub-events as well as the realis status of an event.