Few-shot relation extraction aims to learn to identify the relation between two entities based on very limited training examples. Recent efforts found that textual labels (i.e., relation names and relation descriptions) could be extremely useful for learning class representations, which will benefit the few-shot learning task. However, what is the best way to leverage such label information in the learning process is an important research question. Existing works largely assume such textual labels are always present during both learning and prediction. In this work, we argue that such approaches may not always lead to optimal results. Instead, we present a novel approach called label prompt dropout, which randomly removes label descriptions in the learning process. Our experiments show that our approach is able to lead to improved class representations, yielding significantly better results on the few-shot relation extraction task.
翻译:最近的努力发现,文字标签(即关系名称和关系说明)对于学习班的表述可能极为有用,这将有利于少数的学习任务。然而,在学习过程中利用这种标签信息的最佳方式是一个重要的研究问题。现有工作在很大程度上假定在学习和预测期间总是存在这种文字标签。在这项工作中,我们争论说,这种方式不一定总能带来最佳结果。相反,我们提出了一种新颖的方法,称为标签即时退出,随意删除学习过程中的标签说明。我们的实验表明,我们的方法能够导致改进课程表述,在少数关系提取任务上产生更好的结果。