Few-shot classification in Named Entity Recognition Task

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.

In proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing

References in corpus (2)

• Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition
• Improving One-Shot Learning through Fusing Side Information

Cited by in corpus (8)

• Few-Shot Named Entity Recognition: A Comprehensive Study
• Example-Based Named Entity Recognition
• Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning
• Vector Projection Network for Few-shot Slot Tagging in Natural Language Understanding
• Sensitive Data Detection with High-Throughput Neural Network Models for Financial Institutions
• Augmented Natural Language for Generative Sequence Labeling
• Linguistically-Enriched and Context-Aware Zero-shot Slot Filling
• Few-shot Intent Classification and Slot Filling with Retrieved Examples