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
250
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
210
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
270
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
180
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
190
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
180
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
310
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
390
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
260
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
230
Other Decks in Research
See All in Research
Proposal of an Information Delivery Method for Electronic Paper Signage Using Human Mobility as the Communication Medium / ICCE-Asia 2025
yumulab
0
260
LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection
satai
3
640
言語モデルから言語について語る際に押さえておきたいこと
eumesy
PRO
5
1.8k
姫路市 -都市OSの「再実装」-
hopin
0
1.7k
Upgrading Multi-Agent Pathfinding for the Real World
kei18
0
530
2026 東京科学大 情報通信系 研究室紹介 (大岡山)
icttitech
0
960
明日から使える!研究効率化ツール入門
matsui_528
10
5.5k
【SIGGRAPH Asia 2025】Lo-Fi Photograph with Lo-Fi Communication
toremolo72
0
140
ForestCast: Forecasting Deforestation Risk at Scale with Deep Learning
satai
3
560
SREのためのテレメトリー技術の探究 / Telemetry for SRE
yuukit
13
3.4k
[IBIS 2025] 深層基盤モデルのための強化学習驚きから理論にもとづく納得へ
akifumi_wachi
20
9.8k
IEEE AIxVR 2026 Keynote Talk: "Beyond Visibility: Understanding Scenes and Humans under Challenging Conditions with Diverse Sensing"
miso2024
0
130
Featured
See All Featured
エンジニアに許された特別な時間の終わり
watany
106
240k
Done Done
chrislema
186
16k
Breaking role norms: Why Content Design is so much more than writing copy - Taylor Woolridge
uxyall
0
220
SEO for Brand Visibility & Recognition
aleyda
0
4.4k
sira's awesome portfolio website redesign presentation
elsirapls
0
200
Introduction to Domain-Driven Design and Collaborative software design
baasie
1
650
We Are The Robots
honzajavorek
0
200
A brief & incomplete history of UX Design for the World Wide Web: 1989–2019
jct
1
330
Build your cross-platform service in a week with App Engine
jlugia
234
18k
Data-driven link building: lessons from a $708K investment (BrightonSEO talk)
szymonslowik
1
980
Skip the Path - Find Your Career Trail
mkilby
1
88
Site-Speed That Sticks
csswizardry
13
1.1k
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)
• • • • •