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
380
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
SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing
satai
3
590
Dwangoでの漫画データ活用〜漫画理解と動画作成〜@コミック工学シンポジウム2025
kzmssk
0
140
20年前に50代だった人たちの今
hysmrk
0
160
AI Agentの精度改善に見るML開発との共通点 / commonalities in accuracy improvements in agentic era
shimacos
5
1.4k
競合や要望に流されない─B2B SaaSでミニマム要件を決めるリアルな取り組み / Don't be swayed by competitors or requests - A real effort to determine minimum requirements for B2B SaaS
kaminashi
0
950
2026-01-30-MandSL-textbook-jp-cos-lod
yegusa
1
530
Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning
satai
3
580
20251023_くまもと21の会例会_「車1割削減、渋滞半減、公共交通2倍」をめざして.pdf
trafficbrain
0
190
2026年3月1日(日)福島「除染土」の公共利用をかんがえる
atsukomasano2026
0
380
社内データ分析AIエージェントを できるだけ使いやすくする工夫
fufufukakaka
1
950
Off-Policy Evaluation and Learning for Matching Markets
yudai00
0
100
【SIGGRAPH Asia 2025】Lo-Fi Photograph with Lo-Fi Communication
toremolo72
0
130
Featured
See All Featured
Everyday Curiosity
cassininazir
0
150
VelocityConf: Rendering Performance Case Studies
addyosmani
333
24k
Technical Leadership for Architectural Decision Making
baasie
3
270
A Modern Web Designer's Workflow
chriscoyier
698
190k
Heart Work Chapter 1 - Part 1
lfama
PRO
5
35k
How to optimise 3,500 product descriptions for ecommerce in one day using ChatGPT
katarinadahlin
PRO
1
3.5k
We Have a Design System, Now What?
morganepeng
55
8k
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.1k
Paper Plane (Part 1)
katiecoart
PRO
0
5.1k
Building Experiences: Design Systems, User Experience, and Full Site Editing
marktimemedia
0
430
Become a Pro
speakerdeck
PRO
31
5.8k
Why Mistakes Are the Best Teachers: Turning Failure into a Pathway for Growth
auna
0
74
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)
• • • • •