方法对比

	基于RoBERTa的分类	RoBERTa-based 分类微调
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2019	2019
提出者	Liu, Y. et al. (Facebook AI Research / University of Washington)	Liu, Y. et al. (Meta AI / University of Washington)
类型	Pre-trained transformer fine-tuned for sequence classification	Pretrained transformer fine-tuned for classification
开创性文献	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.	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:1907.11692.
别名	RoBERTa classifier, RoBERTa text classification, Robustly Optimized BERT Classification, RoBERTa fine-tuning for classification	RoBERTa fine-tuning, RoBERTa classifier, fine-tuned RoBERTa, RoBERTa sequence classification
相关	5	5
摘要	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.	Fine-tuned RoBERTa-based classification adapts the RoBERTa pretrained transformer — itself a robustly retrained variant of BERT — to a specific text classification task by appending a classification head and continuing training on labeled examples. It consistently achieves state-of-the-art or near-state-of-the-art performance on sentiment analysis, topic classification, toxicity detection, and similar NLP tasks.