2019/07/23の文献紹介で発表
Decomposable NeuralParaphrase Generation
View Slide
https://arxiv.org/abs/1906.09741
••••
•••
•
••
•• = [1, … , ] • = [1, … , ]
• •• ℎ= BiLSTM( ; ℎ−1, ℎ+1)• = LSTM ℎ, −1; −1• = GumbelSoftmax(, )
•• = − encoderz(, )• 1:−1, = − encoderz, 1:−1
•• 1:−1, = σ1:−1, (|1:−1, )
• 0, 1• = LSTM 0; 1; −1; −1• 1:−1, = GumbelSoftmax ,
••∗ = 0∗ = 1
•• ℒ = σ=1 log 1:−1, + σ=1 log ∗ + σ=1 log (∗ 1:−1,
••From 1(best) to 4(worst)
•••••
yumeto
smatsumori
masakat0
keyakkie
cheerfularge
upura
sensetime_japan
koheishinden
eqpresents
kosuken
smartfukushilab1
kei18
kuehara
thekraken
matthewcrist
smashingmag
mojombo
nonsquared
shpigford
tmm1
wjessup
bcantrill
paulrobertlloyd
destraynor
moore