Recently decades have witnessed the empirical success of framing Knowledge Graph (KG) embeddings via language models. However, language model-based KG embeddings are usually deployed as static artifacts, which are challenging to modify without re-training after deployment. To address this issue, we propose a new task of editing language model-based KG embeddings in this paper. The proposed task aims to enable data-efficient and fast updates to KG embeddings without damaging the performance of the rest. We build four new datasets: E-FB15k237, A-FB15k237, E-WN18RR, and A-WN18RR, and evaluate several knowledge editing baselines demonstrating the limited ability of previous models to handle the proposed challenging task. We further propose a simple yet strong baseline dubbed KGEditor, which utilizes additional parametric layers of the hyper network to edit/add facts. Comprehensive experimental results demonstrate that KGEditor can perform better when updating specific facts while not affecting the rest with low training resources. Code and datasets will be available in https://github.com/zjunlp/PromptKG/tree/main/deltaKG.

翻译：近年来，将知识图谱嵌入与语言模型相结合的方法在实证中取得了成功。然而，基于语言模型的知识图谱嵌入通常作为静态构件部署，在部署后若不重新训练则难以修改。为解决这一问题，本文提出了一项新任务：编辑基于语言模型的知识图谱嵌入。该任务旨在以数据高效且快速的方式更新知识图谱嵌入，同时不影响其余部分的性能。我们构建了四个新数据集：E-FB15k237、A-FB15k237、E-WN18RR 和 A-WN18RR，并评估了多种知识编辑基线方法，揭示出先前模型在处理这一挑战性任务时能力有限。我们进一步提出一个简单而强大的基线模型 KGEditor，该模型利用超网络的额外参数层来编辑/添加事实。综合实验结果表明，KGEditor 在更新特定事实时性能更优，且对剩余部分影响极小，同时训练资源消耗低。代码和数据集将在 https://github.com/zjunlp/PromptKG/tree/main/deltaKG 提供。