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 are 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。以往的典型解决方案主要利用来自资源丰富领域的数据，通过预训练语言模型（PLMs）获得NER模型，并将其适应到目标领域。由于不同领域实体类型之间的不匹配问题，以往方法通常调整PLM的所有参数，最终为每个领域生成一个全新的NER模型。此外，当前模型仅关注利用单个通用源领域的知识，而未能成功将多个源领域的知识迁移到目标领域。为解决这些问题，我们提出基于文本到文本生成式PLM的跨领域NER协作式领域前缀微调（CP-NER）。具体而言，我们采用文本到文本生成方式，将领域相关的指令作为基础，将知识迁移到新领域的NER任务中，无需结构修改。我们利用冻结的PLM进行协作式领域前缀微调，以激发PLM处理跨多个领域NER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NER任务上均表现更优。代码可在https://github.com/zjunlp/DeepKE/tree/main/example/ner/cross获取。