Papers › Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification

Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification

26 Oct 2020COLING 2020 8arXiv:2010.13641archive 2025-07-28

Timo Schick, Helmut Schmid, Hinrich Schütze

A recent approach for few-shot text classification is to convert textual inputs to cloze questions that contain some form of task description, process them with a pretrained language model and map the predicted words to labels. Manually defining this mapping between words and labels requires both domain expertise and an understanding of the language model's abilities. To mitigate this issue, we devise an approach that automatically finds such a mapping given small amounts of training data. For a number of tasks, the mapping found by our approach performs almost as well as hand-crafted label-to-word mappings.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

timoschick/pet officialmentioned in paperpytorchApache-2.0 report
hannight/amulap mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Few-Shot Text ClassificationGeneral ClassificationLanguage ModelingLanguage ModellingText Classificationtext-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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