Construction of Hyper-Relational Knowledge Graphs Using Pre-Trained Large Language Models
This addresses the limited supervised methods for hyper-relation extraction, which is crucial for building comprehensive knowledge graphs, though it appears incremental with lower precision noted.
The paper tackled the problem of extracting hyper-relations for knowledge graph construction by introducing a zero-shot prompt-based method using GPT-3.5, achieving a recall of 0.77 compared to a baseline.
Extracting hyper-relations is crucial for constructing comprehensive knowledge graphs, but there are limited supervised methods available for this task. To address this gap, we introduce a zero-shot prompt-based method using OpenAI's GPT-3.5 model for extracting hyper-relational knowledge from text. Comparing our model with a baseline, we achieved promising results, with a recall of 0.77. Although our precision is currently lower, a detailed analysis of the model outputs has uncovered potential pathways for future research in this area.