Abstract
Accurate entity linkers have been produced for domains and languages where annotated data (i.e., texts linked to a knowledge base) is available. However, little progress has been made for the settings where no or very limited amounts of labeled data are present (e.g., legal or most scientific domains). In this work, we show how we can learn to link mentions without having any labeled examples, only a knowledge base and a collection of unannotated texts from the corresponding domain. In order to achieve this, we frame the task as a multi-instance learning problem and rely on surface matching to create initial noisy labels. As the learning signal is weak and our surrogate labels are noisy, we introduce a noise detection component in our model: it lets the model detect and disregard examples which are likely to be noisy. Our method, jointly learning to detect noise and link entities, greatly outperforms the surface matching baseline and for a subset of entity categories even approaches the performance of supervised learning.
Abstract (translated)
已经为有注释数据(即链接到知识库的文本)可用的域和语言生成了准确的实体链接器。但是,在没有或数量非常有限的标记数据(例如,法律或大多数科学领域)的环境中,几乎没有取得进展。在这篇文章中,我们展示了如何在没有任何标记的例子的情况下学会链接引用,只有一个知识库和一组来自相应领域的未标记的文本。为了实现这一点,我们将任务定义为一个多实例学习问题,并依靠表面匹配来创建初始噪声标签。由于学习信号较弱,并且我们的代理标签有噪声,因此我们在模型中引入了一个噪声检测组件:它允许模型检测和忽略可能有噪声的示例。我们的方法,联合学习检测噪声和链接实体,大大优于表面匹配基线,对于实体类别的子集,甚至接近监督学习的性能。
URL
https://arxiv.org/abs/1905.07189