Tag
The paper evaluates multiple LLM-based strategies for knowledge entity relation extraction from academic abstracts and full texts, finding that a LoRA-adapted T5 model achieves the best macro F1 scores while hybrid SLM/LLM strategies further improve performance.
Proposes SSDAU, a structured semantic data augmentation method for joint entity and relation extraction that preserves semantic structure by segmenting text based on entity labels and using BERTTopic for topic consistency, significantly outperforming existing augmentation methods.