论文标题
使用标签提示辍学的更好的几个射击关系提取
Better Few-Shot Relation Extraction with Label Prompt Dropout
论文作者
论文摘要
很少有射击关系提取旨在学习基于非常有限的培训示例来确定两个实体之间的关系。最近的努力发现，文本标签（即关系名称和关系描述）对于学习课程表示可能非常有用，这将使几个记录的学习任务受益。但是，在学习过程中利用此类标签信息的最佳方法是一个重要的研究问题。现有作品在很大程度上假设在学习和预测过程中始终存在此类文本标签。在这项工作中，我们认为这种方法可能并不总是会带来最佳结果。取而代之的是，我们提出了一种名为标签提示辍学的新方法，该方法随机删除了学习过程中的标签描述。我们的实验表明，我们的方法能够导致改进的类表征，从而在少数射击关系提取任务上获得更好的结果。
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.
