2INER: Instructive and In-Context Learning on Few-Shot Named Entity Recognition
Jiasheng Zhang, Xikai Liu, Xinyi Lai, Yan feng Gao, Shusen Wang, Yao Hu, Yiqing Lin · 2023
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 textto-text framework for Few-Shot Named Entity Recognition (NER) tasks.Our approach employs instruction finetuning based on Instruc-tionNER (Wang et al., 2022) 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 Extraction, 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.