Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
文献紹介: EditNTS: An Neural Programmer-Interpreter...
Search
Yumeto Inaoka
August 08, 2019
Research
440
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
2019/08/08の文献紹介で発表
Yumeto Inaoka
August 08, 2019
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
230
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
290
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
200
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
210
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
220
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
330
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
260
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
300
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
250
Other Decks in Research
See All in Research
【ローカルAIに向き合う展示会vol.2】液体時間定数型モジュールを用いた オリジナルの双方向エンコーダーモデルNexteraBERT 推論速度向上検討並びにダウンストリーム評価
rikkabotan7
0
190
VLMの推論を高速化する視覚トークン削減の仕組み
tattaka
2
310
論文紹介: Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind
hisaokatsumi
0
160
MIRU2026 チュートリアル講演2:三次元データ処理の動向
nnchiba
6
4.8k
クラウド・AI 時代の研究開発 DX / R&D Digital Transformation
hariby
0
140
進学校の生徒にはア行の苗字が多いのか
ozekinote
0
570
AIエージェント時代のLLM-jpモデルのあるべき姿
k141303
0
630
【中間報告】国会議員の立法・政策実務を支える環境を巡る現状と課題
polipoli
0
580
Sleuthcon Keynote - How Cybercriminals (ab)use AI
fr0gger
0
320
Visual SLAM未来予測 / Future Prediction in Visual SLAM
koide3
1
1k
Cross-Media Information Spaces and Architectures
signer
PRO
0
370
超効率化への挑戦:1bit LLMの現状と展望
yumaichikawa
0
700
Featured
See All Featured
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
46
3k
Why Mistakes Are the Best Teachers: Turning Failure into a Pathway for Growth
auna
0
270
Winning Ecommerce Organic Search in an AI Era - #searchnstuff2025
aleyda
1
2.1k
Odyssey Design
rkendrick25
PRO
2
800
Product Roadmaps are Hard
iamctodd
55
13k
What's in a price? How to price your products and services
michaelherold
247
13k
The Hidden Cost of Media on the Web [PixelPalooza 2025]
tammyeverts
2
500
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
Imperfection Machines: The Place of Print at Facebook
scottboms
270
14k
SERP Conf. Vienna - Web Accessibility: Optimizing for Inclusivity and SEO
sarafernandez
2
1.6k
KATA
mclloyd
PRO
35
15k
Designing for humans not robots
tammielis
254
26k
Transcript
None
None
• • • •
• •
None
None
• • •1:−1 •1:−1 •
• • enc = 1 , … , enc =
ℎ1 enc, … , ℎ enc • = 1 , … , •ℎ enc = LSTMenc 1 , 2 1 ∙ , 2 ∙
• •h enc •ℎ edit 1:−1 • •ℎ edit =
LSTMedit ℎ enc, , ℎ−1 edit, ℎ−1 int • = σ =1 || ℎ = softmax ℎ , ℎ
• •
• •ℎ int = LSTMint ℎ−1 int , −1
• •
• •
•
• • •
• • • •
• • • • •
• •
• •
• •
•
• • • •