PANER: A Paraphrase-Augmented Framework for Low-Resource Named Entity Recognition

TL;DR

This paper introduces PANER, a lightweight few-shot NER framework that combines instruction tuning and paraphrasing-based data augmentation to improve low-resource NER performance, achieving state-of-the-art results.

Contribution

The paper proposes a novel instruction tuning template and a paraphrasing data augmentation technique specifically designed for low-resource NER tasks.

Findings

Achieves an average F1 score of 80.1 on CrossNER datasets.

Paraphrasing improves F1 scores by up to 17 points.

Performs comparably to state-of-the-art models in few-shot and zero-shot settings.

Abstract

Named Entity Recognition (NER) is a critical task that requires substantial annotated data, making it challenging in low-resource scenarios where label acquisition is expensive. While zero-shot and instruction-tuned approaches have made progress, they often fail to generalize to domain-specific entities and do not effectively utilize limited available data. We present a lightweight few-shot NER framework that addresses these challenges through two key innovations: (1) a new instruction tuning template with a simplified output format that combines principles from prior IT approaches to leverage the large context window of recent state-of-the-art LLMs; (2) introducing a strategic data augmentation technique that preserves entity information while paraphrasing the surrounding context, thereby expanding our training data without compromising semantic relationships. Experiments on benchmark datasets show that our method achieves performance comparable to state-of-the-art models on few-shot and zero-shot tasks, with our few-shot approach attaining an average F1 score of 80.1 on the CrossNER datasets. Models trained with our paraphrasing approach show consistent improvements in F1 scores of up to 17 points over baseline versions, offering a promising solution for groups with limited NER training data and compute power.