Compară metode

	Răspuns la întrebări prin ajustare fină	Clasificare bazată pe RoBERTa
Domeniu	Învățare profundă	Învățare profundă
Familie	Machine learning	Machine learning
Anul apariției	2016–2019	2019
Autorul original	Devlin et al. (BERT); Rajpurkar et al. (SQuAD benchmark)	Liu, Y. et al. (Facebook AI Research / University of Washington)
Tip	Transfer learning / fine-tuning for extractive or generative QA	Pre-trained transformer fine-tuned for sequence classification
Sursa seminală	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of NAACL-HLT 2019, 4171–4186.	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.
Denumiri alternative	fine-tuned QA, neural QA with fine-tuning, extractive QA fine-tuning, reading comprehension fine-tuning	RoBERTa classifier, RoBERTa text classification, Robustly Optimized BERT Classification, RoBERTa fine-tuning for classification
Înrudite	5	5
Rezumat	Fine-Tuned Question Answering adapts a large pre-trained language model — such as BERT, RoBERTa, or a GPT-family model — to answer natural-language questions over a given context passage or knowledge base. The model learns to locate answer spans or generate free-form answers by continuing training on labeled QA pairs after general-purpose pre-training.	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.