The zero-shot relation triplet extraction (ZeroRTE) task aims to extract relation triplets from a piece of text with unseen relation types. The seminal work adopts the pre-trained generative model to generate synthetic samples for new relations. However, current generative models lack the optimization process of model generalization on different tasks during training, and thus have limited generalization capability. For this reason, we propose a novel generative meta-learning framework which exploits the `learning-to-learn' ability of meta-learning to boost the generalization capability of generative models. Specifically, we first design a task-aware generative model which can learn the general knowledge by forcing the optimization process to be conducted across multiple tasks. Based on it, we then present three generative meta-learning approaches designated for three typical meta-learning categories. Extensive experimental results demonstrate that our framework achieves a new state-of-the-art performance for the ZeroRTE task.

翻译：零样本关系三元组抽取任务旨在从文本中抽取包含未见关系类型的关系三元组。开创性工作采用预训练生成模型为新型关系生成合成样本。然而，当前生成模型在训练过程中缺乏对不同任务泛化能力的优化机制，导致其泛化能力受限。为此，我们提出一种新型生成式元学习框架，该框架利用元学习"学会学习"的能力来增强生成模型的泛化能力。具体而言，我们首先设计了一种任务感知型生成模型，通过强制优化过程跨多个任务进行来学习通用知识。在此基础上，我们进一步提出了三种分别针对典型元学习类别的生成式元学习方法。大量实验结果表明，我们的框架在零样本关系三元组抽取任务上达到了新的最优性能。