Relation Extraction with Instance-Adapted Predicate Descriptions
This is an incremental improvement for relation extraction tasks in domains like biomedical research and general information extraction.
The paper tackled relation extraction by proposing a dual-encoder architecture with instance-specific predicate representations, achieving F1 score improvements of 1% to 2% over state-of-the-art methods on biomedical and general domain datasets.
Relation extraction (RE) is a standard information extraction task playing a major role in downstream applications such as knowledge discovery and question answering. Although decoder-only large language models are excelling in generative tasks, smaller encoder models are still the go to architecture for RE. In this paper, we revisit fine-tuning such smaller models using a novel dual-encoder architecture with a joint contrastive and cross-entropy loss. Unlike previous methods that employ a fixed linear layer for predicate representations, our approach uses a second encoder to compute instance-specific predicate representations by infusing them with real entity spans from corresponding input instances. We conducted experiments on two biomedical RE datasets and two general domain datasets. Our approach achieved F1 score improvements ranging from 1% to 2% over state-of-the-art methods with a simple but elegant formulation. Ablation studies justify the importance of various components built into the proposed architecture.