Few-shot Knowledge Extraction for Manufacturing Domain Based on Large Language Models

Knowledge graph is an effective tool for managing and representing multi-source heterogeneous data in the manufacturing domain. As the key to building knowledge graph, knowledge extraction in the manufacturing domain usually faces the problem of insufficient labeled data, which usually requires huge annotation costs and further limits the application of knowledge graphs in the manufacturing domain. We propose a novel entity-relation joint extraction method in this paper, which aims to use the powerful text generation capability of large language models to achieve data augmentation in the manufacturing domain, and finally efficient extraction of manufacturing knowledge in the few-shot scenario. Besides, in order to further alleviate the hallucination problem caused by the large model generation process, this paper designs a discriminator to filter duplicate and irrelevant data. Experimental results show that our proposed model is effective and robust in the manufacturing domain compared with the state-of-the-art model and ablation experiments prove the effectiveness of each module proposed.