CS224N (2) 썸네일형 리스트형 [CS224n] Lecture 7(3)-8 Attention (3) Attention : New neural technique (3) Attention : New neural technique Seq2Seq (Prob) : Bottleneck problem -> How can we get more info during the translation ? (Sol) Attention Core idea on each step of decoder, use direct connection to the encoder to focus on a particular part of the source sequence attention score -> attention distribution Why do we need both encoder rnn & decoder rnn ? -> ".. [CS224n] Lecture 7 - Translation, Seq2Seq Machine Transaltion : new task Seq2Seq : new neural architecture (1) Machine Transaltion : New task SMT ( Statistical Machine Translation ) Bayes Rule Learning alignment need large amount of parallel data! ↓ Alignment : correspondence between particular words (Prob) one - to - many , many - to - many Alignment a = latent variable explicitly specified X Decoding (Q) How to compute this argmax? (A.. 이전 1 다음
