השוואת שיטות

	למידת ייצוגים ב-NLP באמצעות למידה השוואתית	סיווג טקסט
תחום	כריית טקסט	כריית טקסט
משפחה	Process / pipeline	Process / pipeline
שנת המקור	2020–2021	—
הוגה השיטה	Gao, Yao & Chen (SimCSE, 2021); Khosla et al. (Supervised Contrastive, 2020)	—
סוג	Self-supervised / supervised representation learning	Supervised NLP classification task
מקור מכונן	Gao, T., Yao, X., & Chen, D. (2021). SimCSE: Simple Contrastive Learning of Sentence Embeddings. Proceedings of EMNLP 2021.	Joachims, T. (1998). Text Categorization with Support Vector Machines: Learning with Many Relevant Features. ECML 1998. Lecture Notes in Computer Science, vol 1398. Springer.
כינויים	SimCSE, contrastive sentence embeddings, ContrastiveBERT, Karşıtlık Öğrenmesi — NLP (Contrastive Learning)	text categorization, document classification, topic classification, metin sınıflandırma
קשורות	4	4
תקציר	Contrastive learning for NLP is a representation-learning technique — popularised by SimCSE (Gao et al., 2021) and Supervised Contrastive Learning (Khosla et al., 2020) — that trains a text encoder by pulling embeddings of similar text pairs together while pushing embeddings of dissimilar pairs apart. The result is a dense, high-quality embedding space that can be learned with no labels at all, or with minimal supervision, making it especially valuable when annotated data are scarce.	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.