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
280
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
220
Other Decks in Research
See All in Research
時系列データに対する解釈可能な 決定木クラスタリング
mickey_kubo
2
860
SkySense : A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery
satai
3
290
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
0
120
NLP Colloquium
junokim
1
180
EarthSynth: Generating Informative Earth Observation with Diffusion Models
satai
3
160
研究テーマのデザインと研究遂行の方法論
hisashiishihara
5
1.5k
SSII2025 [TS3] 医工連携における画像情報学研究
ssii
PRO
2
1.3k
Computational OT #4 - Gradient flow and diffusion models
gpeyre
0
350
Towards a More Efficient Reasoning LLM: AIMO2 Solution Summary and Introduction to Fast-Math Models
analokmaus
2
710
Combinatorial Search with Generators
kei18
0
520
Google Agent Development Kit (ADK) 入門 🚀
mickey_kubo
2
1.5k
大規模な2値整数計画問題に対する 効率的な重み付き局所探索法
mickey_kubo
1
310
Featured
See All Featured
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
26k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
Music & Morning Musume
bryan
46
6.7k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
34
6k
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
229
22k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
126
53k
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
8
440
Scaling GitHub
holman
461
140k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
332
22k
The Cost Of JavaScript in 2023
addyosmani
51
8.8k
Fireside Chat
paigeccino
38
3.6k
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)
• • • • •