Cross-domain NER is a challenging task to address the low-resource problem in practical scenarios. Previous typical solutions mainly obtain a NER model by pre-trained language models (PLMs) with data from a rich-resource domain and adapt it to the target domain. Owing to the mismatch issue among entity types in different domains, previous approaches normally tune all parameters of PLMs, ending up with an entirely new NER model for each domain. Moreover, current models only focus on leveraging knowledge in one general source domain while failing to successfully transfer knowledge from multiple sources to the target. To address these issues, we introduce Collaborative Domain-Prefix Tuning for cross-domain NER (CP-NER) based on text-to-text generative PLMs. Specifically, we present text-to-text generation grounding domain-related instructors to transfer knowledge to new domain NER tasks without structural modifications. We utilize frozen PLMs and conduct collaborative domain-prefix tuning to stimulate the potential of PLMs to handle NER tasks across various domains. Experimental results on the Cross-NER benchmark show that the proposed approach has flexible transfer ability and performs better on both one-source and multiple-source cross-domain NER tasks. Codes will be available in https://github.com/zjunlp/DeepKE/tree/main/example/ner/cross.

翻译：跨领域命名实体识别是一项旨在解决实际场景中低资源问题的具有挑战性的任务。以往典型解决方案主要通过利用资源丰富领域的数据，基于预训练语言模型获得命名实体识别模型，并将其适配到目标领域。由于不同领域间实体类型存在不匹配问题，传统方法通常需要对预训练语言模型的所有参数进行微调，从而为每个领域生成全新的命名实体识别模型。此外，现有模型仅专注于利用单一通用源领域的知识，未能成功实现从多个源领域向目标领域的知识迁移。针对这些问题，我们提出基于文本到文本生成式预训练语言模型的协作领域前缀微调方法（CP-NER）用于跨领域命名实体识别。具体而言，我们通过领域相关指令的文本到文本生成式对齐，在不进行结构修改的情况下将知识迁移至新领域的命名实体识别任务。采用冻结的预训练语言模型并进行协作领域前缀微调，以激发预训练语言模型处理跨领域命名实体识别任务的潜力。在Cross-NER基准上的实验结果表明，所提方法具有灵活的迁移能力，在单源和多源跨领域命名实体识别任务中均表现更优。相关代码将在 https://github.com/zjunlp/DeepKE/tree/main/example/ner/cross 中提供。