From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer

TL;DR

This paper introduces GenKGC, a novel approach that transforms knowledge graph completion into a sequence-to-sequence generation task using pre-trained language models, improving performance and inference speed.

Contribution

It proposes relation-guided demonstration and entity-aware hierarchical decoding, and releases a new large-scale Chinese knowledge graph dataset for research.

Findings

Achieves better or comparable performance on three datasets.

Provides faster inference compared to previous methods.

Introduces a new Chinese knowledge graph dataset AliopenKG500.

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.