A Survey on Transfer Learning in Natural Language Processing

Abstract

Deep learning models usually require a huge amount of data. However, these large datasets are not always attainable. This is common in many challenging NLP tasks. Consider Neural Machine Translation, for instance, where curating such large datasets may not be possible specially for low resource languages. Another limitation of deep learning models is the demand for huge computing resources. These obstacles motivate research to question the possibility of knowledge transfer using large trained models. The demand for transfer learning is increasing as many large models are emerging. In this survey, we feature the recent transfer learning advances in the field of NLP. We also provide a taxonomy for categorizing different transfer learning approaches from the literature.

References in corpus (10)

• Distilling the Knowledge in a Neural Network
• Language Models are Few-Shot Learners
• Deep Domain Confusion: Maximizing for Domain Invariance
• Convolutional Neural Networks for Sentence Classification
• Regularizing and Optimizing LSTM Language Models
• Machine Comprehension Using Match-LSTM and Answer Pointer
• BERT and PALs: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning
• Transfer Learning for Named-Entity Recognition with Neural Networks
• Knowledge Adaptation: Teaching to Adapt
• Evolution of transfer learning in natural language processing