事件抽取指的是从非结构化文本中抽取事件信息,并将其以结构化形式呈现出来的任务。例如从“毛泽东1893 年出生于湖南湘潭”这句话中抽取事件{类型:出生,人物:毛泽东,时间:1893 年,出生地:湖南湘潭}。 事件抽取任务通常包含事件类型识别和事件元素填充两个子任务。

VIP内容

事件参数抽取(EAE)是信息抽取时发现特定事件角色参数的重要任务。在本研究中,我们将EAE转换为一个基于问题的完形填空任务,并对固定离散标记模板性能进行实证分析。由于生成人工注释的问题模板通常是耗时且耗费劳动,我们进一步提出了一种名为“Learning to Ask”的新方法,该方法可以在无需人工注释的情况下学习EAE的优化问题模板。我们使用ACE-2005数据集进行实验,结果表明我们基于优化提问的方法在fewshot和全监督设定中都取得了最先进的性能。

成为VIP会员查看完整内容
0
6

最新内容

Space situational awareness typically makes use of physical measurements from radar, telescopes, and other assets to monitor satellites and other spacecraft for operational, navigational, and defense purposes. In this work we explore using textual input for the space situational awareness task. We construct a corpus of 48.5k news articles spanning all known active satellites between 2009 and 2020. Using a dependency-rule-based extraction system designed to target three high-impact events -- spacecraft launches, failures, and decommissionings, we identify 1,787 space-event sentences that are then annotated by humans with 15.9k labels for event slots. We empirically demonstrate a state-of-the-art neural extraction system achieves an overall F1 between 53 and 91 per slot for event extraction in this low-resource, high-impact domain.

0
0
下载
预览

最新论文

Space situational awareness typically makes use of physical measurements from radar, telescopes, and other assets to monitor satellites and other spacecraft for operational, navigational, and defense purposes. In this work we explore using textual input for the space situational awareness task. We construct a corpus of 48.5k news articles spanning all known active satellites between 2009 and 2020. Using a dependency-rule-based extraction system designed to target three high-impact events -- spacecraft launches, failures, and decommissionings, we identify 1,787 space-event sentences that are then annotated by humans with 15.9k labels for event slots. We empirically demonstrate a state-of-the-art neural extraction system achieves an overall F1 between 53 and 91 per slot for event extraction in this low-resource, high-impact domain.

0
0
下载
预览
参考链接
父主题
Top
微信扫码咨询专知VIP会员