jiphyeonjeon / season3

Jiphyeonjeon Season 3
MIT License
39 stars 6 forks source link

Attention Is All You Need #35

Open jinmang2 opened 2 years ago

jinmang2 commented 2 years ago

집현전 중급반 스터디

Abstract

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

sehooni commented 2 years ago

발표 자료는 아래 링크에서 확인하실 수 있습니다! https://drive.google.com/file/d/1L7HDfCZ8GVxtOTMIHU2mH6CYqWzwT5N-/view?usp=sharing

jinmang2 commented 2 years ago
sangmandu commented 2 years ago

위 링크는 잘못된 것 같습니다 https://www.youtube.com/watch?v=aFlWGqVzPbo&list=PL2tRglRS_GqjCcBVM26gYNdoOnX12lLIh&index=11