Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference

By Timo Schick, Hinrich Schütze. 2020

1,862 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Prompting & Reasoning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Luke S. Zettlemoyer
  3. Yejin Choi
  4. Jianfeng Gao
  5. Graham Neubig
  6. Percy Liang
  7. Hannaneh Hajishirzi
  8. Noah A. Smith

In Computer Vision and Pattern Recognition

  1. Luc Van Gool
  2. Mohit Bansal
  3. Dacheng Tao
  4. Trevor Darrell
  5. Xiaogang Wang
  6. Ming-Hsuan Yang
  7. Jitendra Malik
  8. Andrew Zisserman

In Prompting & Reasoning

  1. Luke S. Zettlemoyer
  2. Hannaneh Hajishirzi
  3. Timo Schick
  4. Swaroop Mishra
  5. Hinrich Schütze
  6. Yejin Choi
  7. Mohit Bansal
  8. Chitta Baral

Citations in the corpus