Compara mètodes

	Unitat recurrent amb portes (GRU)	Classificació basada en BERT
Camp	Aprenentatge profund	Aprenentatge profund
Família	Machine learning	Machine learning
Any d'origen	2014	2019
Autor original	Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y.	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language)
Tipus	Recurrent neural network with gating	Pre-trained language model with fine-tuning
Font seminal	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.	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.
Àlies	GRU, GRU network, gated RNN, GRU cell	BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS
Relacionats	3	4
Resum	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.	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.