Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Speaker Deck
PRO
Sign in
Sign up for free
文献紹介: Decomposable Neural Paraphrase Generation
Yumeto Inaoka
July 23, 2019
Research
0
120
文献紹介: Decomposable Neural Paraphrase Generation
2019/07/23の文献紹介で発表
Yumeto Inaoka
July 23, 2019
Tweet
Share
More Decks by Yumeto Inaoka
See All by Yumeto Inaoka
文献紹介: Quantity doesn’t buy quality syntax with neural language models
yumeto
1
70
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
95
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
74
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
77
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
50
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
150
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
180
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
130
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
100
Other Decks in Research
See All in Research
Meta x2 理解するExplainable AI
kionawalker
0
430
Research Paper Introduction in IR Reading 2022 Fall
takuyaa
0
2.2k
小1にルービックキューブを教えてみた 〜群論スポーツの教育とパターン認知〜
itakigawa
0
140
【西多摩電波調査】調査報告書
5g_digitalservicetmg
0
270
Making oRAT, Go
patrickwardle
0
700
Revisiting Over-smoothing in BERT from the Perspective of Graph
eumesy
PRO
0
310
Tecnologias Emergentes: reflexões a partir da Intelectualidade de Milton Santos
taisso
0
150
世界観を考察するのが好き?Sound Horizonはいいぞ / Introduction to Sound Horizon
hyuyukun
0
790
20221219TXPMedical勉強会
tadook
1
350
RecSys22読み会_MTRS
daimoriwaki
0
340
[IR Reading 2022秋 論文紹介] Expressions Causing Differences in Emotion Recognition in Social Networking Service Documents (CIKM'22) / IR Reading 2022 Autumn
shunk031
1
440
正確な推薦は無条件に信頼できるか?
kuri8ive
3
630
Featured
See All Featured
How GitHub (no longer) Works
holman
298
140k
Building Adaptive Systems
keathley
27
1.3k
The Pragmatic Product Professional
lauravandoore
21
3.4k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
227
16k
The Straight Up "How To Draw Better" Workshop
denniskardys
226
130k
Large-scale JavaScript Application Architecture
addyosmani
499
110k
Infographics Made Easy
chrislema
235
17k
Fontdeck: Realign not Redesign
paulrobertlloyd
74
4.3k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
152
13k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
15
1.2k
Bash Introduction
62gerente
601
210k
We Have a Design System, Now What?
morganepeng
37
5.9k
Transcript
Decomposable Neural Paraphrase Generation
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 , = σ 1:−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)
• • • • •