Methods › General › Semi-Supervised Learning Methods › Pattern-Exploiting Training
Pattern-Exploiting Training
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.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Near matches the lookup lists, each a different name: Pattern-Exploiting Training (PET); Pattern Induction; pattern diversity; Pattern Inference; Pattern-Aware LDL-MoE; Decision Pattern Shift (DPS); Pattern Stability Score (PSS); pattern-aligned patch sampling.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 6 · with a code link: 3 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran: none of the 6 tagged papers has a Syntology run on record
Page 1 of 1: papers 1 to 6 of 6, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Exploring Data Augmentation Methods on Social Media Corpora 3 Mar 2023 · 0 repositories · arXiv:2303.02198
-
Enhancing Tabular Reasoning with Pattern Exploiting Training 21 Oct 2022 · 0 repositories · arXiv:2210.12259
-
Quantifying the effect of color processing on blood and damaged tissue detection in Whole Slide Images 26 Sep 2022 · 1 repository
-
Few-shot Named Entity Recognition with Cloze Questions 24 Nov 2021 · 0 repositories · arXiv:2111.12421
-
Exploiting Cloze-Questions for Few-Shot Text Classification and Natural Language Inference 1 Apr 2021 · 1 repository
-
Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference 21 Jan 2020 · 6 repositories · arXiv:2001.07676
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.
Usage over time archive 2025-07-28
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
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