手法を比較

	文埋め込みによる転移学習	RoBERTaベースの分類
分野	深層学習	深層学習
系統	Machine learning	Machine learning
提唱年	2017–2019	2019
提唱者	Reimers, N. & Gurevych, I. (SBERT); Conneau, A. et al. (InferSent)	Liu, Y. et al. (Facebook AI Research / University of Washington)
種類	Transfer learning / sentence representation	Pre-trained transformer fine-tuned for sequence classification
原典	Reimers, N. & Gurevych, I. (2019). Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3982–3992.	Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692.
別名	sentence embedding transfer learning, pre-trained sentence encoder fine-tuning, SBERT transfer learning, sentence representation transfer	RoBERTa classifier, RoBERTa text classification, Robustly Optimized BERT Classification, RoBERTa fine-tuning for classification
関連	5	5
概要	Transfer Learning with Sentence Embeddings takes a large pre-trained encoder — such as Sentence-BERT or the Universal Sentence Encoder — that already encodes general language knowledge into fixed-length vectors, and adapts it to a new task or domain with little additional labelled data. The pre-trained representations give a head start that often outperforms task-specific models trained from scratch on modest corpora.	RoBERTa-based Classification applies the RoBERTa pre-trained transformer — trained more robustly than BERT with dynamic masking and larger batches — to text categorisation tasks by adding a lightweight classification head on top of the [CLS] token representation and fine-tuning the entire model on labelled examples. It consistently matches or outperforms BERT on standard NLP benchmarks.