Upgrade to PRO for Only $50/Year—Limited-Time Offer! 🔥
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
240
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
200
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
250
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
170
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
180
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
170
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
290
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
360
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
240
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
230
Other Decks in Research
See All in Research
「リアル×スキマ時間」を活用したUXリサーチ 〜新規事業を前に進めるためのUXリサーチプロセスの設計〜
techtekt
PRO
0
170
ロボット学習における大規模検索技術の展開と応用
denkiwakame
1
170
GPUを利用したStein Particle Filterによる点群6自由度モンテカルロSLAM
takuminakao
0
620
Thirty Years of Progress in Speech Synthesis: A Personal Perspective on the Past, Present, and Future
ktokuda
0
120
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
kurita
1
290
EcoWikiRS: Learning Ecological Representation of Satellite Images from Weak Supervision with Species Observation and Wikipedia
satai
3
420
POI: Proof of Identity
katsyoshi
0
120
日本語新聞記事を用いた大規模言語モデルの暗記定量化 / LLMC2025
upura
0
360
思いつきが武器になる:研究というゲームを始めよう / Ideas Are Your Equipments : Let the Game of Research Begin!
ks91
PRO
0
100
Pythonでジオを使い倒そう! 〜それとFOSS4G Hiroshima 2026のご紹介を少し〜
wata909
0
1.2k
cvpaper.challenge 10年の軌跡 / cvpaper.challenge a decade-long journey
gatheluck
3
1k
地域丸ごとデイサービス「Go トレ」の紹介
smartfukushilab1
0
590
Featured
See All Featured
Context Engineering - Making Every Token Count
addyosmani
9
510
Leading Effective Engineering Teams in the AI Era
addyosmani
8
1.3k
A Tale of Four Properties
chriscoyier
162
23k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
254
22k
Building Applications with DynamoDB
mza
96
6.8k
Imperfection Machines: The Place of Print at Facebook
scottboms
269
13k
Thoughts on Productivity
jonyablonski
73
5k
Done Done
chrislema
186
16k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
55
3.1k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
9
1k
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)
• • • • •