arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.03022cs.CL
收藏

用于事件论元提取的资源增强神经模型

Resource-Enhanced Neural Model for Event Argument Extraction

Amazon AI(亚马逊人工智能)

Jie Ma, Shuai Wang, Rishita Anubhai, Miguel Ballesteros, Yaser Al-Onaizan

摘要:

事件论元抽取(EAE)的目的是识别事件的论元,并对这些论元所扮演的角色进行分类。尽管前期工作做了很大努力,但仍存在许多挑战:(1)数据稀缺。(2)捕获远程依赖关系,特别是事件触发器和远程事件参数之间的连接。(3)将事件触发器信息集成到候选参数表示中。对于(1),我们探索以不同的方式使用未标记的数据。对于(2),我们建议使用一个语法参与的Transformer,它可以利用依赖解析来指导注意力机制。对于(3),我们提出了一种具有几种类型的依赖于编码器的序列表示的编码器感知的序列编码器。我们还支持从带有黄金实体注释的文本或纯文本中提取参数。在英语ACE2005测试集上的实验表明,该方法达到了新的水平。

英文摘要:

Event argument extraction (EAE) aims to identify the arguments of an event and classify the roles that those arguments play. Despite great efforts made in prior work, there remain many challenges: (1) Data scarcity. (2) Capturing the long-range dependency, specifically, the connection between an event trigger and a distant event argument. (3) Integrating event trigger information into candidate argument representation. For (1), we explore using unlabeled data in different ways. For (2), we propose to use a syntax-attending Transformer that can utilize dependency parses to guide the attention mechanism. For (3), we propose a trigger-aware sequence encoder with several types of trigger-dependent sequence representations. We also support argument extraction either from text annotated with gold entities or from plain text. Experiments on the English ACE2005 benchmark show that our approach achieves a new state-of-the-art.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑