Cross-domain Named Entity Recognition (NER) transfers knowledge learned from a rich-resource source domain to improve the learning in a low-resource target domain. Most existing works are designed based on the sequence labeling framework, defining entity detection and type prediction as a monolithic process. However, they typically ignore the discrepant transferability of these two sub-tasks: the former locating spans corresponding to entities is largely domain-robust, while the latter owns distinct entity types across domains. Combining them into an entangled learning problem may contribute to the complexity of domain transfer. In this work, we propose the novel divide-and-transfer paradigm in which different sub-tasks are learned using separate functional modules for respective cross-domain transfer. To demonstrate the effectiveness of divide-and-transfer, we concretely implement two NER frameworks by applying this paradigm with different cross-domain transfer strategies. Experimental results on 10 different domain pairs show the notable superiority of our proposed frameworks. Experimental analyses indicate that significant advantages of the divide-and-transfer paradigm over prior monolithic ones originate from its better performance on low-resource data and a much greater transferability. It gives us a new insight into cross-domain NER. Our code is available at our github.

跨域命名实体识别 (NER) 将从丰富资源源域中学到的知识转移到资源匮乏的目标域中改进学习。大多数现有工作都是基于序列标记框架设计的，将实体检测和类型预测定义为一个整体过程。然而，他们通常忽略这两个子任务的差异可转移性：前一个对应于实体的定位范围在很大程度上是域鲁棒性的，而后者拥有跨域的不同实体类型。将它们组合成一个纠缠的学习问题可能会增加域迁移的复杂性。在这项工作中，我们提出了新颖的划分和转移范式，其中使用单独的功能模块来学习不同的子任务以进行各自的跨域转移。为了证明划分和转移的有效性，我们通过应用这种范式和不同的跨域转移策略来具体实现两个 NER 框架。 10 个不同域对的实验结果表明我们提出的框架具有显着的优越性。实验分析表明，分而转移范式相对于之前的整体范式的显着优势源于其在低资源数据上的更好性能和更大的可转移性。它让我们对跨域 NER 有了新的认识。我们的代码可以在我们的 github 上找到。