In relation triplet extraction (RTE), recognizing unseen (new) relations for which there are no training instances is a challenging task. Efforts have been made to recognize unseen relations based on question-answering models or relation descriptions. However, these approaches miss the semantic information about connections between seen and unseen relations. In this paper, We propose a prompt-based model with semantic knowledge augmentation (ZS-SKA) to recognize unseen relations under the zero-shot setting. We present a new word-level analogy-based sentence translation rule and generate augmented instances with unseen relations from instances with seen relations using that new rule. We design prompts with weighted virtual label construction based on an external knowledge graph to integrate semantic knowledge information learned from seen relations. Instead of using the actual label sets in the prompt template, we construct weighted virtual label words. We learn the representations of both seen and unseen relations with augmented instances and prompts. We then calculate the distance between the generated representations using prototypical networks to predict unseen relations. Extensive experiments conducted on three public datasets FewRel, Wiki-ZSL, and NYT, show that ZS-SKA outperforms state-of-the-art methods under the zero-shot scenarios. Our experimental results also demonstrate the effectiveness and robustness of ZS-SKA.

翻译：在关系三元组抽取（RTE）中，识别未见（新）关系（即不存在训练实例的关系）是一项具有挑战性的任务。已有研究尝试基于问答模型或关系描述来识别未见关系，但这些方法忽略了已见关系与未见关系之间连接的语义信息。本文中，我们提出了一种基于提示的语义知识增强模型（ZS-SKA），用于在零样本设置下识别未见关系。我们提出了一种新的基于词级类比法的句子翻译规则，并利用该规则从已见关系实例中生成带有未见关系的增强实例。我们基于外部知识图谱设计带有加权虚拟标签构建的提示，以整合从已见关系中学到的语义知识信息。不同于在提示模板中使用实际标签集，我们构建了加权虚拟标签词。我们通过增强实例和提示学习已见与未见关系的表示，然后利用原型网络计算生成的表示之间的距离以预测未见关系。在三个公开数据集FewRel、Wiki-ZSL和NYT上进行的大量实验表明，ZS-SKA在零样本场景下优于现有最先进方法。我们的实验结果也证明了ZS-SKA的有效性和鲁棒性。