AMR-RE: Abstract Meaning Representations for Retrieval-Based In-Context Learning in Relation Extraction

AbstractExisting in-context learning (ICL) methods for relation extraction (RE) often prioritize language similarity over structural similarity, which may result in overlooking entity relationships. We propose an AMR-enhanced retrieval-based ICL method for RE to address this issue. Our model retrieves in-context examples based on semantic structure similarity between task inputs and training samples. We conducted experiments in the supervised setting on four standard English RE datasets. The results show that our method achieves state-of-the-art performance on three datasets and competitive results on the fourth. Furthermore, our method outperforms baselines by a large margin across all datasets in the more demanding unsupervised setting.