arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.15097cs.CLcs.AI
收藏

面向事件链接的论元感知方法

Argument-Aware Approach To Event Linking

Information Science Institute, University of Southern California(南加州大学信息科学研究所);Computer Science Department, University of California, Los Angeles(加州大学洛杉矶分校计算机科学系);Cisco Research(思科研究)

I-Hung Hsu, Zihan Xue, Nilay Pochh, Sahil Bansal, Premkumar Natarajan, Jayanth Srinivasa, Nanyun Peng

AI总结:

本文提出论元感知的事件链接方法,通过标注事件论元增强输入并合成知识库外训练样本,在两个数据集上显著提升了知识库内和知识库外事件链接性能。

摘要:

事件链接将文本中的事件提及与知识库(KB)中的相关节点连接起来。先前的事件链接研究主要借鉴实体链接的方法,忽视了事件的独特特征。与已被广泛探索的实体链接任务相比,事件具有更复杂的结构,并且通过考察其关联的论元可以更有效地区分。此外,事件信息丰富的特性导致事件知识库的稀缺。这强调了事件链接模型需要识别并分类不在知识库中的事件提及为“知识库外(out-of-KB)”,而这一领域受到的关注有限。在这项工作中,我们通过引入一种论元感知的方法来应对这些挑战。首先,我们通过用带标签的事件论元信息增强输入文本,改进事件链接模型,促进对事件提及关键信息的识别。随后,为了帮助模型处理“知识库外”场景,我们通过对事件论元进行受控操作,从知识库内实例合成知识库外的训练示例。我们在两个测试数据集上的实验显示,在知识库内和知识库外场景中均有显著提升,其中知识库外评估取得了显著的22%改进。

英文摘要:

Event linking connects event mentions in text with relevant nodes in a knowledge base (KB). Prior research in event linking has mainly borrowed methods from entity linking, overlooking the distinct features of events. Compared to the extensively explored entity linking task, events have more complex structures and can be more effectively distinguished by examining their associated arguments. Moreover, the information-rich nature of events leads to the scarcity of event KBs. This emphasizes the need for event linking models to identify and classify event mentions not in the KB as ``out-of-KB,'' an area that has received limited attention. In this work, we tackle these challenges by introducing an argument-aware approach. First, we improve event linking models by augmenting input text with tagged event argument information, facilitating the recognition of key information about event mentions. Subsequently, to help the model handle ``out-of-KB'' scenarios, we synthesize out-of-KB training examples from in-KB instances through controlled manipulation of event arguments. Our experiment across two test datasets showed significant enhancements in both in-KB and out-of-KB scenarios, with a notable 22% improvement in out-of-KB evaluations.

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。

↑