论文标题
分解的元学习，用于几个命名实体识别
Decomposed Meta-Learning for Few-Shot Named Entity Recognition
论文作者
论文摘要
几个名称的实体识别（NER）系统旨在仅基于几个标记的示例来识别新颖的class命名实体。在本文中，我们提出了一种分解的元学习方法，该方法通过依次处理几个镜头检测和使用元学习的几个射击实体来解决几个问题的问题。特别是，我们将几个射击跨度检测作为一个序列标记问题，并通过引入模型 - 不合稳定元学习（MAML）算法来训练跨度检测器，以找到一个可以快速适应新实体类的良好模型参数初始化。对于少数拍摄的实体键入，我们建议MAML-Protonet，即MAML增强原型网络，以找到一个可以更好地区分不同实体类的文本跨度表示的良好嵌入空间。各种基准的广泛实验表明，我们的方法比先前的方法实现了卓越的性能。
Few-shot named entity recognition (NER) systems aim at recognizing novel-class named entities based on only a few labeled examples. In this paper, we present a decomposed meta-learning approach which addresses the problem of few-shot NER by sequentially tackling few-shot span detection and few-shot entity typing using meta-learning. In particular, we take the few-shot span detection as a sequence labeling problem and train the span detector by introducing the model-agnostic meta-learning (MAML) algorithm to find a good model parameter initialization that could fast adapt to new entity classes. For few-shot entity typing, we propose MAML-ProtoNet, i.e., MAML-enhanced prototypical networks to find a good embedding space that can better distinguish text span representations from different entity classes. Extensive experiments on various benchmarks show that our approach achieves superior performance over prior methods.
