InstructionNER: A Multi-Task Instruction-Based Generative Framework for Few-shot NER
This addresses the challenge of adapting prompt-based methods to sequence labeling tasks like NER for low-resource scenarios, though it is incremental in building on existing generative approaches.
The authors tackled the problem of few-shot named entity recognition (NER) by reformulating it as a generation task with multi-task instructions, achieving consistent outperformance over baselines on five datasets.
Recently, prompt-based methods have achieved significant performance in few-shot learning scenarios by bridging the gap between language model pre-training and fine-tuning for downstream tasks. However, existing prompt templates are mostly designed for sentence-level tasks and are inappropriate for sequence labeling objectives. To address the above issue, we propose a multi-task instruction-based generative framework, named InstructionNER, for low-resource named entity recognition. Specifically, we reformulate the NER task as a generation problem, which enriches source sentences with task-specific instructions and answer options, then inferences the entities and types in natural language. We further propose two auxiliary tasks, including entity extraction and entity typing, which enable the model to capture more boundary information of entities and deepen the understanding of entity type semantics, respectively. Experimental results show that our method consistently outperforms other baselines on five datasets in few-shot settings.