Compară metode

	Model Secvență-la-Secvență	Mecanismul de atenție	Reglajul fin BERT	Atenție Multi-Capete (Multi-Head Self-Attention)
Domeniu	Învățare profundă	Învățare profundă	Învățare profundă	Învățare profundă
Familie	Machine learning	Machine learning	Machine learning	Machine learning
Anul apariției	2014	2015	2019	2017
Autorul original	Sutskever, I.; Cho, K.	Bahdanau, D.; Luong, M.T.	Devlin, J. et al.	Vaswani, A. et al.
Tip	Encoder-decoder neural network (deep learning)	Neural attention layer (encoder-decoder)	Transfer learning (fine-tuning a pre-trained transformer)	Attention mechanism (Transformer core)
Sursa seminală	Sutskever, I., Vinyals, O. & Le, Q. V. (2014). Sequence to Sequence Learning with Neural Networks. NeurIPS.	Bahdanau, D., Cho, K. & Bengio, Y. (2015). Neural Machine Translation by Jointly Learning to Align and Translate. ICLR.	Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL.	Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS.
Denumiri alternative	Dizi-Dizi Modeli (Seq2Seq — Encoder-Decoder), encoder-decoder model, seq2seq, sequence to sequence learning	Dikkat Mekanizması (Bahdanau / Luong Attention), dikkat mekanizmasi, neural attention, additive attention	BERT İnce Ayar (Fine-Tuning), BERT ince ayar, fine-tuning BERT, transfer learning with BERT	Öz-Dikkat ve Çok Başlı Dikkat (Multi-Head Self-Attention), öz-dikkat, multi-head attention, scaled dot-product attention
Înrudite	5	5	5	5
Rezumat	The sequence-to-sequence (Seq2Seq) model, introduced by Sutskever, Vinyals and Le and by Cho and colleagues in 2014, is an encoder-decoder neural network that maps a variable-length input sequence to a variable-length output sequence. It is the foundation of machine translation, text summarization, dialogue systems and code generation.	The attention mechanism, introduced by Bahdanau, Cho and Bengio in 2015 and refined by Luong, Pham and Manning the same year, lets a sequence decoder dynamically learn which of the encoder's outputs to focus on at each step. Before the Transformer, it substantially improved machine-translation quality by freeing models from compressing an entire input into a single fixed vector.	BERT fine-tuning, building on the BERT model introduced by Devlin and colleagues in 2019, re-trains a pre-trained BERT model on a small labelled dataset for a target task such as classification, named-entity recognition, or question answering. Through transfer learning it reaches high performance even with relatively little task-specific data.	Multi-head self-attention, introduced by Vaswani and colleagues in 2017, is the mechanism that lets every position in a sequence compute its relationship to all other positions in parallel. It is the core of the Transformer architecture and the foundation underneath BERT, GPT, and T5.