Knowledge Guided Metric Learning for Few-Shot Text Classification

Abstract

The training of deep-learning-based text classification models relies heavily on a huge amount of annotation data, which is difficult to obtain. When the labeled data is scarce, models tend to struggle to achieve satisfactory performance. However, human beings can distinguish new categories very efficiently with few examples. This is mainly due to the fact that human beings can leverage knowledge obtained from relevant tasks. Inspired by human intelligence, we propose to introduce external knowledge into few-shot learning to imitate human knowledge. A novel parameter generator network is investigated to this end, which is able to use the external knowledge to generate relation network parameters. Metrics can be transferred among tasks when equipped with these generated parameters, so that similar tasks use similar metrics while different tasks use different metrics. Through experiments, we demonstrate that our method outperforms the state-of-the-art few-shot text classification models.

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Prototypical Networks for Few-shot Learning
• Few-shot Text Classification with Distributional Signatures
• When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification

Cited by in corpus (2)

• Meta-learning for Few-shot Natural Language Processing: A Survey
• What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data