Relation Extraction with Instance-Adapted Predicate Descriptions
Abstract: 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 three different RE datasets from both general and biomedical domains. 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.
Paper Type: Long
Research Area: Information Extraction
Research Area Keywords: relation extraction, contrastive learning, document-level extraction
Contribution Types: Publicly available software and/or pre-trained models
Languages Studied: English
Submission Number: 2907
Loading