Knowledge graph embedding (KGE) models represent each entity and relation of
a knowledge graph (KG) with low-dimensional embedding vectors. These methods
have recently been applied to KG link prediction and question answering over
incomplete KGs (KGQA). KGEs typically create an embedding for each entity in
the graph, which results in large model sizes on real-world graphs with
millions of entities. For downstream tasks these atomic entity representations
often need to be integrated into a multi stage pipeline, limiting their
utility. We show that an off-the-shelf encoder-decoder Transformer model can
serve as a scalable and versatile KGE model obtaining state-of-the-art results
for KG link prediction and incomplete KG question answering. We achieve this by
posing KG link prediction as a sequence-to-sequence task and exchange the
triple scoring approach taken by prior KGE methods with autoregressive
decoding. Such a simple but powerful method reduces the model size up to 98%
compared to conventional KGE models while keeping inference time tractable.
After finetuning this model on the task of KGQA over incomplete KGs, our
approach outperforms baselines on multiple large-scale datasets without
extensive hyperparameter tuning.

本研究使用 Transformer 模型代替传统知识图谱嵌入模型 (KGE) 的原子嵌入表示，将 KG link prediction 问题转化为序列到序列任务以及使用自回归解码。相比于传统 KGE 模型，这种简单而强大的方法在保持推理时间可控的同时，将模型大小减少了多达 98％，在不进行过多超参数调整的情况下，在多个大型数据集上的表现优于基线。