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 2106.09558cs.CL
收藏

开放关系抽取的元素干预

Element Intervention for Open Relation Extraction

University of Chinese Academy of Sciences(中国科学院大学);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)

Fangchao Liu, Lingyong Yan, Hongyu Lin, Xianpei Han, Le Sun

摘要:

开放式关系抽取的目标是对引用同一底层关系的关系实例进行聚类,这是一般关系抽取的关键步骤。目前的OpenRE模型通常是在远程监督生成的数据集上训练的,这往往会导致模型不稳定,容易崩溃。在本文中,我们从因果关系的角度重新审视OpenRE的过程。通过使用结构因果模型制定OpenRE,我们确定上述问题源于从实体和上下文到关系类型的虚假相关性。为了解决这个问题,我们进行\emph{Element Intervention},分别干预的背景和实体,以获得潜在的因果关系的影响。我们还提供了两个具体的实现的干预措施的基础上,实体排名和上下文对比。在无监督关系抽取数据集上的实验结果表明,我们的方法优于以前的最先进的方法,并在不同的数据集上具有鲁棒性。

英文摘要:

Open relation extraction aims to cluster relation instances referring to the same underlying relation, which is a critical step for general relation extraction. Current OpenRE models are commonly trained on the datasets generated from distant supervision, which often results in instability and makes the model easily collapsed. In this paper, we revisit the procedure of OpenRE from a causal view. By formulating OpenRE using a structural causal model, we identify that the above-mentioned problems stem from the spurious correlations from entities and context to the relation type. To address this issue, we conduct \emph{Element Intervention}, which intervenes on the context and entities respectively to obtain the underlying causal effects of them. We also provide two specific implementations of the interventions based on entity ranking and context contrasting. Experimental results on unsupervised relation extraction datasets show that our methods outperform previous state-of-the-art methods and are robust across different datasets.

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。

↑