From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer

Abstract

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.

Accepted by WWW 2022 Poster

References in corpus (5)

• Autoregressive Entity Retrieval
• Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners
• Ontology-enhanced Prompt-tuning for Few-shot Learning
• OntoProtein: Protein Pretraining With Gene Ontology Embedding
• ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge Graphs

Cited by in corpus (6)

• Unifying Large Language Models and Knowledge Graphs: A Roadmap
• When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities
• Socially Aware Synthetic Data Generation for Suicidal Ideation Detection Using Large Language Models
• Prompting Disentangled Embeddings for Knowledge Graph Completion with Pre-trained Language Model
• Embedding Ontologies via Incorporating Extensional and Intensional Knowledge
• NeocorRAG: Less Irrelevant Information, More Explicit Evidence, and More Effective Recall via Evidence Chains