Method evidence record
Few-Shot Text Classification
Few-shot text classification assigns documents to classes using only a handful of labelled examples per class. Building on advances by Gao et al. (2021) and the prompt-free SetFit approach of Tunstall et al. (2022), it leans on prototypical networks, MAML, or fine-tuning of a large pretrained model to learn from scarce labels.
Source record
Citations copied verbatim from the method’s source record. No claim-level verification is inferred from them.
Few-Shot Text Classification
Taxonomic method record · process-pipeline / text-mining
- Gao, T., Fisch, A. & Chen, D. (2021). Making Pre-trained Language Models Better Few-shot Learners. ACL. · DOI 10.18653/v1/2021.acl-long.295
- Tunstall, L., Reimers, N., Jo, U.E.S., Bates, L., Korat, D., Wasserblat, M. & Pereg, O. (2022). Efficient Few-Shot Learning Without Prompts. arXiv. · DOI 10.48550/arXiv.2209.11055
Curated claims
Claims persisted in the evidence ledger, each with its own assessment.
No curated claims yet
This view does not invent a claim assessment when the ledger has none.
Related methods
Generated from the method graph and shown as machine-suggested relations — no evidence claim is inferred.