Methoden vergleichen

	Zero-Shot-Klassifikation – Textklassifikation ohne Trainingsdaten	Textklassifizierung
Fachgebiet	Text Mining	Text Mining
Familie	Process / pipeline	Process / pipeline
Entstehungsjahr	2019	—
Urheber	Yin, Hay & Roth	—
Typ	NLP text-classification task	Supervised NLP classification task
Wegweisende Quelle	Yin, W., Hay, J. & Roth, D. (2019). Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach. EMNLP, 3914-3923.	Joachims, T. (1998). Text Categorization with Support Vector Machines: Learning with Many Relevant Features. ECML 1998. Lecture Notes in Computer Science, vol 1398. Springer.
Aliasnamen	zero-shot text classification, entailment-based classification, Sıfır Atışlı Sınıflandırma (Zero-Shot Classification)	text categorization, document classification, topic classification, metin sınıflandırma
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.	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.