Uncertainty Sentence Sampling by Virtual Adversarial Perturbation
This work addresses annotation cost reduction for sentence understanding tasks, but it is incremental as it builds on existing methods for active learning.
The paper tackled the problem of reducing annotation costs in active learning for sentence understanding by proposing VAPAL, a framework that combines predictive uncertainty and sample diversity using virtual adversarial perturbation, and it performed equally well or better than strong baselines on four datasets including AGNEWS and IMDB.
Active learning for sentence understanding attempts to reduce the annotation cost by identifying the most informative examples. Common methods for active learning use either uncertainty or diversity sampling in the pool-based scenario. In this work, to incorporate both predictive uncertainty and sample diversity, we propose Virtual Adversarial Perturbation for Active Learning (VAPAL) , an uncertainty-diversity combination framework, using virtual adversarial perturbation (Miyato et al., 2019) as model uncertainty representation. VAPAL consistently performs equally well or even better than the strong baselines on four sentence understanding datasets: AGNEWS, IMDB, PUBMED, and SST-2, offering a potential option for active learning on sentence understanding tasks.