השוואת שיטות

	זיהוי ישויות מוכרות בלמידה עצמית	למידת מעט דוגמאות	זיהוי ישויות מוכרות (NER)
תחום	למידה עמוקה	למידת מכונה	כריית טקסט
משפחה	Machine learning	Machine learning	Process / pipeline
שנת המקור	2018–2019	2011–2017	—
הוגה השיטה	Devlin et al.; community-evolved from BERT-era self-supervised pretraining	Lake, B. M.; Vinyals, O.; Finn, C. et al.	—
סוג	Sequence labeling via self-supervised pretraining + fine-tuning	Meta-learning / low-data learning paradigm	NLP sequence-labelling task
מקור מכונן	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, 4171–4186.	Vinyals, O., Blundell, C., Lillicrap, T., Wierstra, D., & Kavukcuoglu, K. (2016). Matching Networks for One Shot Learning. Advances in Neural Information Processing Systems (NeurIPS), 29.	Nadeau, D. & Sekine, S. (2007). A survey of named entity recognition. Lingvisticae Investigationes.
כינויים	Self-supervised NER, SS-NER, label-efficient NER, pre-trained NER	FSL, low-shot learning, k-shot learning, meta-learning for few examples	NER, entity tagging, Adlandırılmış Varlık Tanıma (NER)
קשורות	2	4	3
תקציר	Self-supervised named entity recognition (NER) combines large-scale self-supervised pretraining — such as masked language modeling — with token-level fine-tuning to identify and classify named entities in text. By learning general linguistic representations before seeing any entity labels, the model achieves strong performance even when annotated NER training data is scarce.	Few-shot learning is a machine learning paradigm that trains models to recognize new classes or solve new tasks from only a handful of labeled examples — typically one to five — by leveraging prior knowledge acquired from a large, related training distribution. It is especially relevant in domains where labeling is expensive, scarce, or structurally limited.	Named entity recognition (NER) is a natural-language-processing task that automatically detects and labels entities in text — such as people, organisations, locations, and dates. Surveyed by Nadeau and Sekine (2007) and later advanced with neural architectures by Lample et al. (2016), it turns free-running text into tagged spans that downstream tools can use.