Few-shot classification in Named Entity Recognition Task

被引：139

作者：

Fritzler, Alexander ^{[2
,3
]}

Logacheva, Varvara ^{[1
]}

Kretov, Maksim ^{[1
]}

机构：

[1] Moscow Inst Phys & Technol, Neural Networks & Deep Learning Lab, Moscow, Russia

[2] Quantum Brains, Moscow, Russia

[3] Higher Sch Econ, Moscow, Russia

来源：

SAC '19: PROCEEDINGS OF THE 34TH ACM/SIGAPP SYMPOSIUM ON APPLIED COMPUTING | 2019年

关键词：

Named Entity Recognition; Prototypical networks; Few-shot learning; Semi-supervised learning; Transfer learning;

D O I：

10.1145/3297280.3297378

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

For many natural language processing (NLP) tasks the amount of annotated data is limited. This urges a need to apply semi-supervised learning techniques, such as transfer learning or meta-learning. In this work we tackle Named Entity Recognition (NER) task using Prototypical Network - a metric learning technique. It learns intermediate representations of words which cluster well into named entity classes. This property of the model allows classifying words with extremely limited number of training examples, and can potentially be used as a zero-shot learning method. By coupling this technique with transfer learning we achieve well-performing classifiers trained on only 20 instances of a target class.

引用

页码：993 / 1000

页数：8