arXiv:2001.07676cs.CL
Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference
Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.
Abstract
Some NLP tasks can be solved in a fully unsupervised fashion by providing a pretrained language model with "task descriptions" in natural language (e.g., Radford et al., 2019). While this approach underperforms its supervised counterpart, we show in this work that the two ideas can be combined: We introduce Pattern-Exploiting Training (PET), a semi-supervised training procedure that reformulates input examples as cloze-style phrases to help language models understand a given task. These phrases are then used to assign soft labels to a large set of unlabeled examples. Finally, standard supervised training is performed on the resulting training set. For several tasks and languages, PET outperforms supervised training and strong semi-supervised approaches in low-resource settings by a large margin.
The headline is clickbait (GPT-3 is about language modeling/generation, and there's ZERO mention of that in this work), but the actual work is interesting and the paper is worth a read. To the OP: please consider changing the headline to "Exploiting Cloze Questions for Few Shot…
cs702View on HNParent context