Detecting Subevents using Discourse and Narrative Features
Detecting Subevents using Discourse and Narrative Features
复制标题
DOI：
10.18653/v1/p19-1471
复制
发表时间：
2019-07
期刊：
影响因子：
--
通讯作者：
Mohammed Aldawsari;Mark A. Finlayson
中科院分区：
文献类型：
--
作者：
Mohammed Aldawsari;Mark A. Finlayson
识别事件的内部结构是一项具有挑战性的语言处理任务，对文本理解具有重要意义。我们提出了一个监督模型，用于自动识别一个事件何时是另一个事件的子事件。在以前的工作的基础上，我们介绍了几个新的功能，特别是话语和叙事功能，显着提高了以前的国家的最先进的性能。错误分析进一步证明了这些功能的实用性。我们评估我们的模型上只有两个注释语料库与事件层次结构：Hieve和情报界语料库。在这两个语料库上都没有对先前的系统进行评估。我们的模型在这两个语料库上的表现都优于以前的系统，在情报社区语料库上实现了0.74 BLANC F1，在Hieve语料库上实现了0.70 F1，分别比以前的模型提高了15和5个百分点。
Recognizing the internal structure of events is a challenging language processing task of great importance for text understanding. We present a supervised model for automatically identifying when one event is a subevent of another. Building on prior work, we introduce several novel features, in particular discourse and narrative features, that significantly improve upon prior state-of-the-art performance. Error analysis further demonstrates the utility of these features. We evaluate our model on the only two annotated corpora with event hierarchies: HiEve and the Intelligence Community corpus. No prior system has been evaluated on both corpora. Our model outperforms previous systems on both corpora, achieving 0.74 BLANC F1 on the Intelligence Community corpus and 0.70 F1 on the HiEve corpus, respectively a 15 and 5 percentage point improvement over previous models.