论文标题
从语言模型中蒸馏出超呼气关系：关于零击分类学诱导的有效性
Distilling Hypernymy Relations from Language Models: On the Effectiveness of Zero-Shot Taxonomy Induction
论文作者
论文摘要
在本文中，我们分析了零拍的分类学学习方法，这些学习方法基于通过提示和句子评分从语言模型中提取知识的方法。我们表明，尽管它们很简单，但这些方法的表现优于某些监督策略，并且在适当条件下与当前最新的策略具有竞争力。我们还表明，提示的统计和语言特性决定了下游性能。
In this paper, we analyze zero-shot taxonomy learning methods which are based on distilling knowledge from language models via prompting and sentence scoring. We show that, despite their simplicity, these methods outperform some supervised strategies and are competitive with the current state-of-the-art under adequate conditions. We also show that statistical and linguistic properties of prompts dictate downstream performance.
