手法を比較

	ゼロショット分類	Few-Shot Text Classification	テキスト分類
分野	テキストマイニング	テキストマイニング	テキストマイニング
系統	Process / pipeline	Process / pipeline	Process / pipeline
提唱年	2019	—	—
提唱者	Yin, Hay & Roth	—	—
種類	NLP text-classification task	NLP text-classification task (low-resource)	Supervised NLP classification task
原典	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.	Joachims, T. (1998). Text Categorization with Support Vector Machines: Learning with Many Relevant Features. ECML 1998. Lecture Notes in Computer Science, vol 1398. Springer.
別名	zero-shot text classification, entailment-based classification, Sıfır Atışlı Sınıflandırma (Zero-Shot Classification)	few-shot learning for text, Az Atışlı Metin Sınıflandırma (Few-Shot)	text categorization, document classification, topic classification, metin sınıflandırma
関連	3	4	4
概要	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.	Text classification, also called text categorization, is a supervised natural-language-processing task that automatically assigns documents to predefined categories. Building on the support-vector-machine approach to text categorization established by Joachims (1998) and consolidated in the text-mining literature by Aggarwal and Zhai (2012), it powers tasks such as spam detection and topic classification by learning from labelled examples.