事件抽取指的是從非結構化文本中抽取事件信息,並將其以結構化形式呈現出來的任務。例如從“毛澤東1893 年出生於湖南湘潭”這句話中抽取事件{類型:出生,人物:毛澤東,時間:1893 年,出生地:湖南湘潭}。 事件抽取任務通常包含事件類型識別和事件元素填充兩個子任務。

VIP內容

事件參數抽取(EAE)是信息抽取時發現特定事件角色參數的重要任務。在本研究中,我們將EAE轉換為一個基於問題的完形填空任務,並對固定離散標記模板性能進行實證分析。由於生成人工注釋的問題模板通常是耗時且耗費勞動,我們進一步提出了一種名為“Learning to Ask”的新方法,該方法可以在無需人工注釋的情況下學習EAE的優化問題模板。我們使用ACE-2005數據集進行實驗,結果表明我們基於優化提問的方法在fewshot和全監督設定中都取得了最先進的性能。

成為VIP會員查看完整內容
0
6
0

最新內容

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
0
下載
預覽

最新論文

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
0
下載
預覽
參考鏈接
父主題
Top
微信掃碼谘詢專知VIP會員
Top