论文标题
具有自描述网络的几个命名实体识别
Few-shot Named Entity Recognition with Self-describing Networks
论文作者
论文摘要
很少有人需要从有限实例中有效捕获信息，并从外部资源中转移有用的知识。在本文中，我们提出了一种自我描述的机制，用于几个弹药，可以通过描述实体类型和使用通用概念集来有效地利用说明性实例，并从外部资源中精确地转移知识。具体而言，我们设计了自称网络（SDNET），这是一个SEQ2SEQ生成模型，可以通过概念普遍描述提及，将新颖的实体类型自动映射到概念上，并自适应地识别实体。我们用大型语料库预先培训SDNET，并对来自不同领域的8个基准测试进行实验。实验表明，SDNET在所有基准测试基准上实现了竞争性能，并在6个基准上实现了新的最先进的表现，从而证明了其有效性和鲁棒性。
Few-shot NER needs to effectively capture information from limited instances and transfer useful knowledge from external resources. In this paper, we propose a self-describing mechanism for few-shot NER, which can effectively leverage illustrative instances and precisely transfer knowledge from external resources by describing both entity types and mentions using a universal concept set. Specifically, we design Self-describing Networks (SDNet), a Seq2Seq generation model which can universally describe mentions using concepts, automatically map novel entity types to concepts, and adaptively recognize entities on-demand. We pre-train SDNet with large-scale corpus, and conduct experiments on 8 benchmarks from different domains. Experiments show that SDNet achieves competitive performances on all benchmarks and achieves the new state-of-the-art on 6 benchmarks, which demonstrates its effectiveness and robustness.
