where we cannot manually access and annotate a lot of data, as well as for low-resource tasks in different languages

We thank all the reviewers for their time and insightful feedback about our work. Many of the recent few-shot learning works focus on computer vision compared to NLU tasks. We leverage self-training with several advances to bridge this gap. R1 (Q1) raises an important point with respect to developing a sound annotation scheme. Similar baselines reported for active learning [Gal et al., 2017] and preference learning [Houlsby et al., UDA [Xie et al., 2019] and self-training with noisy student [Xie et al., 2020] show these techniques to work best with Additionally, for IMDB longer sequence length plays a big role.