Methoden vergleichen

	Zero-Shot-Klassifikation – Textklassifikation ohne Trainingsdaten	Few-Shot Text Classification
Fachgebiet	Text Mining	Text Mining
Familie	Process / pipeline	Process / pipeline
Entstehungsjahr	2019	—
Urheber	Yin, Hay & Roth	—
Typ	NLP text-classification task	NLP text-classification task (low-resource)
Wegweisende Quelle	Yin, W., Hay, J. & Roth, D. (2019). Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach. EMNLP, 3914-3923.	Gao, T., Fisch, A. & Chen, D. (2021). Making Pre-trained Language Models Better Few-shot Learners. ACL.
Aliasnamen	zero-shot text classification, entailment-based classification, Sıfır Atışlı Sınıflandırma (Zero-Shot Classification)	few-shot learning for text, Az Atışlı Metin Sınıflandırma (Few-Shot)
Verwandt	3	4
Zusammenfassung	Zero-shot classification is a natural-language-processing task that assigns text to categories described in plain language without requiring any labelled training data. Formalised as an entailment problem by Yin, Hay and Roth (2019), it lets a large pretrained language model recognise new categories on the fly simply by naming them, enabling rapid adaptation to fresh label sets.	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.