Events are inter-related in documents. Motivated by the one-sense-per-discourse theory, we hypothesize that a participant tends to play consistent roles across multiple events in the same document. However recent work on document-level event argument extraction models each individual event in isolation and therefore causes inconsistency among extracted arguments across events, which will further cause discrepancy for downstream applications such as event knowledge base population, question answering, and hypothesis generation. In this work, we formulate event argument consistency as the constraints from event-event relations under the document-level setting. To improve consistency we introduce the Event-Aware Argument Extraction (EA$^2$E) model with augmented context for training and inference. Experiment results on WIKIEVENTS and ACE2005 datasets demonstrate the effectiveness of EA$^2$E compared to baseline methods.
翻译:在文件方面,活动是相互关联的。我们根据单一思维每期理论,假设参与者往往在同一文件中的多个活动中都发挥一贯的作用。然而,最近关于文件一级活动参数提取模型的工作是孤立地逐个进行的,因此造成各事件之间抽取的参数不一致,这将进一步造成下游应用的差异,如事件知识基础人口、问答和假设生成。在这项工作中,我们将事件参数一致性作为文件一级活动关系的限制。为了提高一致性,我们采用了活动软件提取模型(EA$2$E),加强了培训和推断的背景。WIKIPES和ACE2005数据集的实验结果表明,与基线方法相比,EA$2$E的有效性。