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: EditNTS: An Neural Programmer-Interpreter...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Yumeto Inaoka
August 08, 2019
Research
390
0
Share
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
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
190
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
200
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
190
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
320
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
250
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
270
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
240
Other Decks in Research
See All in Research
typst の使い方:言語学を研究する学生のために
gitomochang
0
400
「AIとWhyを深堀る」をAIと深堀る
iflection
0
350
はじまりの クエスチョンブック —余暇と豊かさにあふれた社会とは?
culturaltransition
PRO
0
400
ウェブ・ソーシャルメディア論文読み会 第36回: The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents (EMNLP, 2025)
hkefka385
0
220
量子コンピュータの紹介
oqtopus
0
290
東京大学工学部計数工学科、計数工学特別講義の説明資料
kikuzo
0
360
Aurora Serverless からAurora Serverless v2への課題と知見を論文から読み解く/Understanding the challenges and insights of moving from Aurora Serverless to Aurora Serverless v2 from a paper
bootjp
6
1.6k
データサイエンティストをめぐる環境の違い2025年版〈一般ビジネスパーソン調査の国際比較〉
datascientistsociety
PRO
0
1.3k
IEEE AIxVR 2026 Keynote Talk: "Beyond Visibility: Understanding Scenes and Humans under Challenging Conditions with Diverse Sensing"
miso2024
0
180
AGI4OPT:自然言語から数理最適化を導くエ ージェントスキル Translating Human Intent into Mathematical Optimization
mickey_kubo
0
100
Collective Predictive Coding and World Models in LLMs: A System 0/1/2/3 Perspective on Hierarchical Physical AI (IEEE SII 2026 Plenary Talk)
tanichu
1
380
台湾モデルに学ぶ詐欺広告対策:市民参加の必要性
dd2030
0
320
Featured
See All Featured
The World Runs on Bad Software
bkeepers
PRO
72
12k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
287
14k
[RailsConf 2023] Rails as a piece of cake
palkan
59
6.5k
Mind Mapping
helmedeiros
PRO
1
190
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.2k
The browser strikes back
jonoalderson
0
1k
Utilizing Notion as your number one productivity tool
mfonobong
4
300
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
25
1.9k
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
560
Leading Effective Engineering Teams in the AI Era
addyosmani
9
1.9k
Java REST API Framework Comparison - PWX 2021
mraible
34
9.3k
The innovator’s Mindset - Leading Through an Era of Exponential Change - McGill University 2025
jdejongh
PRO
1
160
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
• •
• •
•
• • •
• • • •
• • • • •
• •
• •
• •
•
• • • •