Graph-Augmented Relation Extraction Model with LLMs-Generated Support Document
This work addresses limitations in traditional sentence-level relation extraction models for natural language processing by incorporating broader contexts and inter-entity interactions, though it appears incremental as it combines existing methods.
This study tackled sentence-level relation extraction by integrating Graph Neural Networks with Large Language Models to generate contextually enriched support documents, resulting in notable performance improvements across various domains on the CrossRE dataset.
This study introduces a novel approach to sentence-level relation extraction (RE) that integrates Graph Neural Networks (GNNs) with Large Language Models (LLMs) to generate contextually enriched support documents. By harnessing the power of LLMs to generate auxiliary information, our approach crafts an intricate graph representation of textual data. This graph is subsequently processed through a Graph Neural Network (GNN) to refine and enrich the embeddings associated with each entity ensuring a more nuanced and interconnected understanding of the data. This methodology addresses the limitations of traditional sentence-level RE models by incorporating broader contexts and leveraging inter-entity interactions, thereby improving the model's ability to capture complex relationships across sentences. Our experiments, conducted on the CrossRE dataset, demonstrate the effectiveness of our approach, with notable improvements in performance across various domains. The results underscore the potential of combining GNNs with LLM-generated context to advance the field of relation extraction.