Few-shot classification in Named Entity Recognition Task
This addresses the need for efficient few-shot learning in NLP, particularly for Named Entity Recognition, though it is incremental as it adapts existing techniques.
The paper tackled the problem of limited annotated data in Named Entity Recognition by using a Prototypical Network combined with transfer learning, achieving well-performing classifiers trained on only 20 instances per target class.
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.