论文标题
FACTMIX：使用一些标记的内域示例来概括为跨域命名实体识别
FactMix: Using a Few Labeled In-domain Examples to Generalize to Cross-domain Named Entity Recognition
论文作者
论文摘要
几个名称实体识别（NER）对于在有限的资源域中标记的射击至关重要，因此近年来受到了适当的关注。现有的几声方法主要在域内设置下进行评估。相比之下，对于这些固有的忠实模型在跨域NER中如何使用一些标记的域内示例在跨域NER中表现鲜明。本文提出了一种两步以理性的数据增强方法，以提高模型的泛化能力。几个数据集中的结果表明，与先前的最新方法相比，我们的模型无形方法可显着提高跨域NER任务的性能，包括数据增强和及时调用方法。我们的代码可从https://github.com/lifan-yuan/factmix获得。
Few-shot Named Entity Recognition (NER) is imperative for entity tagging in limited resource domains and thus received proper attention in recent years. Existing approaches for few-shot NER are evaluated mainly under in-domain settings. In contrast, little is known about how these inherently faithful models perform in cross-domain NER using a few labeled in-domain examples. This paper proposes a two-step rationale-centric data augmentation method to improve the model's generalization ability. Results on several datasets show that our model-agnostic method significantly improves the performance of cross-domain NER tasks compared to previous state-of-the-art methods, including the data augmentation and prompt-tuning methods. Our codes are available at https://github.com/lifan-yuan/FactMix.
