方法对比

	命名实体识别的迁移学习	[需翻译标题：BERT-based Classification...]
领域	深度学习	深度学习
方法族	Machine learning	Machine learning
起源年份	2010 / 2019	2019
提出者	Pan & Yang (transfer learning); Devlin et al. (BERT-based NER fine-tuning)	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language)
类型	Supervised sequence labeling via pretrained encoder fine-tuning	Pre-trained language model with fine-tuning
开创性文献	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT 2019 (pp. 4171–4186). Association for Computational Linguistics.
别名	TL-NER, Fine-Tuned NER, Pretrained Model NER, BERT NER	BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS
相关	5	4
摘要	Transfer Learning with Named Entity Recognition (NER) adapts a large pretrained language model — such as BERT, RoBERTa, or a domain-specific encoder — to the task of identifying and classifying named entities (persons, locations, organizations, dates, etc.) in text. By reusing rich linguistic representations learned from massive corpora, this approach requires only modest labeled NER data while achieving state-of-the-art span detection and classification accuracy.	BERT-based Classification fine-tunes Google's Bidirectional Encoder Representations from Transformers model on a labelled text dataset, replacing the generic pre-trained head with a task-specific classification layer. It exploits deep bidirectional context from hundreds of millions of pre-trained parameters to deliver state-of-the-art accuracy on short- and medium-length text classification tasks with relatively modest amounts of labelled data.