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
SSII2025 [SS1] レンズレスカメラ
ssii
PRO
2
980
2025/7/5 応用音響研究会招待講演@北海道大学
takuma_okamoto
1
110
Minimax and Bayes Optimal Best-arm Identification: Adaptive Experimental Design for Treatment Choice
masakat0
0
120
EarthSynth: Generating Informative Earth Observation with Diffusion Models
satai
3
110
Computational OT #1 - Monge and Kantorovitch
gpeyre
0
190
数理最適化に基づく制御
mickey_kubo
5
680
Looking for Escorts in Sydney?
lunsophia
1
120
Computational OT #4 - Gradient flow and diffusion models
gpeyre
0
310
Principled AI ~深層学習時代における課題解決の方法論~
taniai
3
1.2k
Adaptive fusion of multi-modal remote sensing data for optimal sub-field crop yield prediction
satai
3
220
(NULLCON Goa 2025)Windows Keylogger Detection: Targeting Past and Present Keylogging Techniques
asuna_jp
2
550
ストレス計測方法の確立に向けたマルチモーダルデータの活用
yurikomium
0
730
Featured
See All Featured
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
331
22k
Speed Design
sergeychernyshev
32
1k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
161
15k
GraphQLの誤解/rethinking-graphql
sonatard
71
11k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
Fireside Chat
paigeccino
37
3.5k
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
35
2.4k
Designing Experiences People Love
moore
142
24k
For a Future-Friendly Web
brad_frost
179
9.8k
How to train your dragon (web standard)
notwaldorf
96
6.1k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
31
2.4k
Embracing the Ebb and Flow
colly
86
4.7k
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)
• • • • •