# Few-shot classification in Named Entity Recognition Task

## TL;DR

This paper applies Prototypical Networks to NER, enabling effective few-shot and zero-shot classification by learning well-clustered word representations, especially with very limited training data.

## Contribution

It introduces a novel application of Prototypical Networks for NER, demonstrating effective few-shot and zero-shot learning capabilities in this context.

## Key findings

- Achieves high accuracy with only 20 training instances per class
- Enables zero-shot classification of unseen entity types
- Demonstrates the effectiveness of metric learning in NER

## Abstract

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.