Porovnať metódy

	Klasifikácia založená na RoBERTa	Gated Recurrent Unit (GRU)
Odbor	Hlboké učenie	Hlboké učenie
Rodina	Machine learning	Machine learning
Rok vzniku	2019	2014
Tvorca	Liu, Y. et al. (Facebook AI Research / University of Washington)	Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y.
Typ	Pre-trained transformer fine-tuned for sequence classification	Recurrent neural network with gating
Pôvodný zdroj	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.	Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of EMNLP 2014, pp. 1724–1734.
Ďalšie názvy	RoBERTa classifier, RoBERTa text classification, Robustly Optimized BERT Classification, RoBERTa fine-tuning for classification	GRU, GRU network, gated RNN, GRU cell
Príbuzné	5	3
Zhrnutie	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.	The Gated Recurrent Unit (GRU), introduced by Cho et al. in 2014, is a streamlined recurrent neural network that uses two learned gates — an update gate and a reset gate — to selectively retain or discard information across time steps, enabling effective sequence modelling with fewer parameters than LSTM.