2INER: Instructive and In-Context Learning on Few-Shot Named Entity Recognition
Jiasheng Zhang, Xikai Liu, Xinyi Lai, Yan Gao, Shusen Wang, Yao Hu, YIQING LIN
Abstract
Prompt-based learning has emerged as a powerful technique in natural language processing (NLP) due to its ability to leverage pre-training knowledge for downstream few-shot tasks. In this paper, we propose 2INER, a novel text-to-text framework for Few-Shot Named Entity Recognition (NER) tasks. Our approach employs instruction finetuning based on InstructionNER to enable the model to effectively comprehend and process task-specific instructions, including both main and auxiliary tasks. We also introduce a new auxiliary task, called Type Extracting, to enhance the model's understanding of entity types in the overall semantic context of a sentence. To facilitate in-context learning, we concatenate examples to the input, enabling the model to learn from additional contextual information. Experimental results on four datasets demonstrate that our approach outperforms existing Few-Shot NER methods and remains competitive with state-of-the-art standard NER algorithms.
BibTeX
@inproceedings{
zhang2023iner,
title={2{INER}: Instructive and In-Context Learning on Few-Shot Named Entity Recognition},
author={Jiasheng Zhang and Xikai Liu and Xinyi Lai and Yan Gao and Shusen Wang and Yao Hu and YIQING LIN},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=mrARDvuKi2}
}