手法を比較

	NLPにおける対照学習	意味的類似性
分野	テキストマイニング	テキストマイニング
系統	Process / pipeline	Process / pipeline
提唱年	2020–2021	2019
提唱者	Gao, Yao & Chen (SimCSE, 2021); Khosla et al. (Supervised Contrastive, 2020)	Nils Reimers & Iryna Gurevych (Sentence-BERT)
種類	Self-supervised / supervised representation learning	NLP text-comparison task
原典	Gao, T., Yao, X., & Chen, D. (2021). SimCSE: Simple Contrastive Learning of Sentence Embeddings. Proceedings of EMNLP 2021.	Reimers, N. & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. EMNLP.
別名	SimCSE, contrastive sentence embeddings, ContrastiveBERT, Karşıtlık Öğrenmesi — NLP (Contrastive Learning)	semantic textual similarity, text similarity, Anlamsal Benzerlik Analizi
関連	4	4
概要	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.	Semantic similarity analysis measures how close in meaning two texts are, rather than how many words they share on the surface. Building on the Sentence-BERT work of Reimers and Gurevych (2019), it represents each text as a vector and compares those vectors so that paraphrases score high even when their wording differs.