Text-Augmented Open Knowledge Graph Completion via Pre-Trained Language Models
This addresses the problem of limited performance and high expert effort in knowledge graph completion for AI and data science applications, offering an incremental improvement over existing methods.
The paper tackles open knowledge graph completion by proposing TAGREAL, which automatically generates query prompts and retrieves text support to probe pre-trained language models, achieving state-of-the-art performance on two benchmark datasets and outperforming existing methods even with limited training data.
The mission of open knowledge graph (KG) completion is to draw new findings from known facts. Existing works that augment KG completion require either (1) factual triples to enlarge the graph reasoning space or (2) manually designed prompts to extract knowledge from a pre-trained language model (PLM), exhibiting limited performance and requiring expensive efforts from experts. To this end, we propose TAGREAL that automatically generates quality query prompts and retrieves support information from large text corpora to probe knowledge from PLM for KG completion. The results show that TAGREAL achieves state-of-the-art performance on two benchmark datasets. We find that TAGREAL has superb performance even with limited training data, outperforming existing embedding-based, graph-based, and PLM-based methods.