Сравнение на методи

	Класификация, базирана на BERT	Дългосрочна краткосрочна памет (LSTM)
Област	Дълбоко обучение	Дълбоко обучение
Семейство	Machine learning	Machine learning
Година на възникване	2019	1997
Създател	Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (Google AI Language)	Hochreiter, S. & Schmidhuber, J.
Тип	Pre-trained language model with fine-tuning	Recurrent neural network with gated memory cells
Основополагащ източник	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.	Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.
Други названия	BERT classifier, BERT fine-tuning for classification, BERT text classification, BERT-CLS	LSTM, LSTM network, LSTM-RNN, long short-term memory RNN
Свързани	4	4
Резюме	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.	Long Short-Term Memory (LSTM) is a gated recurrent neural network architecture introduced by Hochreiter and Schmidhuber in 1997. It was designed to learn dependencies across long sequences by using dedicated memory cells and three learned gates — forget, input, and output — that control what information is retained, updated, or passed forward at each time step.