So sánh phương pháp

	Hỏi đáp bán giám sát	Phân loại dựa trên BERT
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2006–2020	2019
Người khởi xướng	Multiple (Chapelle et al.; Zhu; Clark et al. for NLP applications)	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language)
Loại	Semi-supervised learning applied to extractive/generative QA	Pre-trained language model with fine-tuning
Công trình gốc	Clark, K., Luong, M.-T., Le, Q. V., & Manning, C. D. (2020). ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In Proceedings of ICLR 2020.	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.
Tên gọi khác	Semi-supervised QA, Self-training for QA, Pseudo-labeled Question Answering, SSL-QA	BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS
Liên quan	6	4
Tóm tắt	Semi-supervised question answering (QA) trains a model on a small labeled set of question-answer pairs, then generates pseudo-labels on a large unlabeled corpus and retrains iteratively. This self-training loop dramatically increases effective training data without the cost of full manual annotation, achieving strong performance on reading comprehension, open-domain QA, and machine reading tasks.	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.