AMR-RE: Abstract Meaning Representations for Retrieval-Based In-Context Learning in Relation Extraction
This addresses the issue of overlooking entity relationships in retrieval-based in-context learning for relation extraction, offering a domain-specific improvement.
The paper tackled the problem of in-context learning for relation extraction by prioritizing structural similarity over language similarity, resulting in state-of-the-art or competitive performance across four standard datasets in both unsupervised and supervised settings.
Existing in-context learning (ICL) methods for relation extraction (RE) often prioritize language similarity over structural similarity, which can lead to overlooking entity relationships. To address this, we propose an AMR-enhanced retrieval-based ICL method for RE. Our model retrieves in-context examples based on semantic structure similarity between task inputs and training samples. Evaluations on four standard English RE datasets show that our model outperforms baselines in the unsupervised setting across all datasets. In the supervised setting, it achieves state-of-the-art results on three datasets and competitive results on the fourth.