Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks
This incremental improvement reduces annotation costs for NLP tasks like radiology report analysis, benefiting medical AI applications.
The paper tackled the problem of few-shot text classification by extending Prototypical Networks with Gaussian prototypes and a regularization term, achieving improved performance over baselines on 17 datasets and enabling out-of-distribution detection.
Large pretrained Transformer-based language models like BERT and GPT have changed the landscape of Natural Language Processing (NLP). However, fine tuning such models still requires a large number of training examples for each target task, thus annotating multiple datasets and training these models on various downstream tasks becomes time consuming and expensive. In this work, we propose a simple extension of the Prototypical Networks for few-shot text classification. Our main idea is to replace the class prototypes by Gaussians and introduce a regularization term that encourages the examples to be clustered near the appropriate class centroids. Experimental results show that our method outperforms various strong baselines on 13 public and 4 internal datasets. Furthermore, we use the class distributions as a tool for detecting potential out-of-distribution (OOD) data points during deployment.