1. 程式人生 > >論文筆記-Sequence to Sequence Learning with Neural Networks

論文筆記-Sequence to Sequence Learning with Neural Networks

map tran between work down all 9.png ever onf

大體思想和RNN encoder-decoder是一樣的,只是用來LSTM來實現。

技術分享圖片

paper提到三個important point:

1)encoder和decoder的LSTM是兩個不同的模型

2)deep LSTM表現比shallow好,選用了4層的LSTM

3)實踐中發現將輸入句子reverse後再進行訓練效果更好。So for example, instead of mapping the sentence a,b,c to the sentence α,β,γ, the LSTM is asked to map c,b,a to α,β,γ, where α, β, γ is the translation of a, b, c. This way, a is in close proximity to α, b is fairly close to β, and so on, a fact that makes it easy for SGD to “establish communication” between the input and the output.

論文筆記-Sequence to Sequence Learning with Neural Networks