From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer
This addresses the problem of extending knowledge graphs with missing triples for AI and data science applications, representing an incremental improvement with novel method adaptations.
The paper tackles knowledge graph completion by converting it into a sequence-to-sequence generation task using a pre-trained language model, achieving better or comparable performance on three datasets and faster inference speed compared to previous methods.
Knowledge graph completion aims to address the problem of extending a KG with missing triples. In this paper, we provide an approach GenKGC, which converts knowledge graph completion to sequence-to-sequence generation task with the pre-trained language model. We further introduce relation-guided demonstration and entity-aware hierarchical decoding for better representation learning and fast inference. Experimental results on three datasets show that our approach can obtain better or comparable performance than baselines and achieve faster inference speed compared with previous methods with pre-trained language models. We also release a new large-scale Chinese knowledge graph dataset AliopenKG500 for research purpose. Code and datasets are available in https://github.com/zjunlp/PromptKG/tree/main/GenKGC.