VirAAL: Virtual Adversarial Active Learning for NLU

Abstract

This paper presents VirAAL 1 , an Active Learning framework based on Adversarial Training. VirAAL aims to reduce the effort of annotation in Natural Language Understanding (NLU). VirAAL is based on Virtual Adversarial Training (VAT), a semisupervised approach that regularizes the model through Local Distributional Smoothness. With that, adversarial perturbations are added to the inputs making the posterior distribution more consistent. Therefore, entropy-based Active Learning becomes robust by querying more informative samples without requiring additional components. The first set of experiments studies the impact of VAT on NLU tasks (joint or not) within low labeled data regimes. The second set shows the effect of VirAAL in an Active Learning (AL) process. Results demonstrate that VAT is robust even on multitask training where the adversarial noise is computed from multiple loss functions. Substantial improvements are observed with entropy-based AL with VirAAL for querying data to annotate. VirAAL is an inexpensive method in terms of AL computation with a positive impact on data sampling. Furthermore, VirAAL decreases annotations in AL up to 80%.