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
7
0

最新內容

0
0
0

最新論文

Eliciting knowledge contained in language models via prompt-based learning has shown great potential in many natural language processing tasks, such as text classification and generation. Whereas, the applications for more complex tasks such as event extraction are less studied, since the design of prompt is not straightforward due to the complicated types and arguments. In this paper, we explore to elicit the knowledge from pre-trained language models for event trigger detection and argument extraction. Specifically, we present various joint trigger/argument prompt methods, which can elicit more complementary knowledge by modeling the interactions between different triggers or arguments. The experimental results on the benchmark dataset, namely ACE2005, show the great advantages of our proposed approach. In particular, our approach is superior to the recent advanced methods in the few-shot scenario where only a few samples are used for training.

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