Methods › General › Semi-Supervised Learning Methods › Pattern-Exploiting Training

Pattern-Exploiting Training

6 papers tagged archive 2025-07-28

Introduced by Timo Schick et al. in Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Pattern-Exploiting Training is 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.

In the case of PET for sentiment classification, first a number of patterns encoding some form of task description are created to convert training examples to cloze questions; for each pattern, a pretrained language model is finetuned. Secondly, the ensemble of trained models annotates unlabeled data. Lastly, a classifier is trained on the resulting soft-labeled dataset.

PaperSource

Papers archive 2025-07-28

6 shown of 6, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 21 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Text Classification3
Few-Shot Learning2
Few-Shot Text Classification2
Language Modeling2
Language Modelling2
Natural Language Inference2
text-classification2
Artifact Detection1
Binary Classification1
Blood Detection1
Color Normalization1
Damaged Tissue Detection1
Data Augmentation1
Diagnostic1
General Classification1
NER1
Named Entity Recognition1
Named Entity Recognition (NER)1
Transfer Learning1
named-entity-recognition1

Usage over time archive 2025-07-28

Papers per year tagged with Pattern-Exploiting Training: 2020 to 2023, peak 2 2 0 2020: 1 paper 2020 2021: 2 papers 2021 2022: 2 papers 2022 2023: 1 paper 2023
Papers per year the archive tags with this method, by the paper's archive date (6 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Semi-Supervised Learning Methods

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections