Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
文献紹介: Decomposable Neural Paraphrase Generation
Search
Yumeto Inaoka
July 23, 2019
Research
0
230
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
180
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
230
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
160
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
170
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
150
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
270
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
340
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
220
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
210
Other Decks in Research
See All in Research
とあるSREの博士「過程」 / A Certain SRE’s Ph.D. Journey
yuukit
6
3.3k
AIによる画像認識技術の進化 -25年の技術変遷を振り返る-
hf149
6
3.6k
なめらかなシステムと運用維持の終わらぬ未来 / dicomo2025_coherently_fittable_system
monochromegane
0
890
Creation and environmental applications of 15-year daily inundation and vegetation maps for Siberia by integrating satellite and meteorological datasets
satai
3
140
引力・斥力を制御可能なランダム部分集合の確率分布
wasyro
0
200
電通総研の生成AI・エージェントの取り組みエンジニアリング業務向けAI活用事例紹介
isidaitc
1
700
Streamlit 総合解説 ~ PythonistaのためのWebアプリ開発 ~
mickey_kubo
1
1.1k
公立高校入試等に対する受入保留アルゴリズム(DA)導入の提言
shunyanoda
0
6.1k
Computational OT #4 - Gradient flow and diffusion models
gpeyre
0
320
AI エージェントを活用した研究再現性の自動定量評価 / scisci2025
upura
1
130
20250502_ABEJA_論文読み会_スライド
flatton
0
180
ASSADS:ASMR動画に合わせて撫でられる感覚を提示するシステムの開発と評価 / ec75-shimizu
yumulab
1
420
Featured
See All Featured
Optimising Largest Contentful Paint
csswizardry
37
3.3k
Intergalactic Javascript Robots from Outer Space
tanoku
271
27k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
Balancing Empowerment & Direction
lara
1
460
What’s in a name? Adding method to the madness
productmarketing
PRO
23
3.5k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
47
9.6k
Docker and Python
trallard
45
3.5k
Writing Fast Ruby
sferik
628
62k
VelocityConf: Rendering Performance Case Studies
addyosmani
332
24k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
45
7.5k
Scaling GitHub
holman
460
140k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
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)
• • • • •