Document-Level In-Context Few-Shot Relation Extraction via Pre-Trained Language Models

TL;DR

This paper introduces a novel in-context few-shot relation extraction framework that leverages pre-trained language models, eliminating the need for fine-tuning, human annotations, and entity recognition, while achieving state-of-the-art results across multiple datasets.

Contribution

The paper presents the first reformulation of document-level relation extraction as an in-context few-shot learning paradigm, enabling efficient adaptation to new LMs and relation types without re-training.

Findings

Achieves state-of-the-art performance on DocRED dataset.

Outperforms over 30 baseline methods across six datasets.

Requires no fine-tuning or human annotations.

Abstract

Document-level relation extraction aims at inferring structured human knowledge from textual documents. State-of-the-art methods for this task use pre-trained language models (LMs) via fine-tuning, yet fine-tuning is computationally expensive and cannot adapt to new relation types or new LMs. As a remedy, we leverage the generalization capabilities of pre-trained LMs and present a novel framework for document-level in-context few-shot relation extraction. Our framework has three strengths: it eliminates the need (1) for named entity recognition and (2) for human annotations of documents, and (3) it can be updated to new LMs without re-training. We evaluate our framework using DocRED, the largest publicly available dataset for document-level relation extraction, and demonstrate that our framework achieves state-of-the-art performance. We further show that our framework actually performs much better than the original labels from the development set of DocRED. Finally, we conduct an extensive benchmark demonstrating the effectiveness of our framework, achieving state-of-the-art results across six relation extraction datasets and outperforming more than 30 baseline methods. Unlike our framework, the baseline methods have large computational overhead (e.g., from fine-tuning). To the best of our knowledge, we are the first to reformulate the document-level relation extraction task as a tailored in-context few-shot learning paradigm.