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
Yumeto Inaoka
August 08, 2019
Research
0
330
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
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
180
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
230
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
150
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
170
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
150
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
270
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
230
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
220
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
210
Other Decks in Research
See All in Research
20250605_新交通システム推進議連_熊本都市圏「車1割削減、渋滞半減、公共交通2倍」から考える地方都市交通政策
trafficbrain
0
440
Collaborative Development of Foundation Models at Japanese Academia
odashi
2
560
近似動的計画入門
mickey_kubo
4
970
プロシェアリング白書2025_PROSHARING_REPORT_2025
circulation
1
860
Streamlit 総合解説 ~ PythonistaのためのWebアプリ開発 ~
mickey_kubo
1
920
データサイエンティストの就労意識~2015→2024 一般(個人)会員アンケートより
datascientistsociety
PRO
0
690
ASSADS:ASMR動画に合わせて撫でられる感覚を提示するシステムの開発と評価 / ec75-shimizu
yumulab
1
380
在庫管理のための機械学習と最適化の融合
mickey_kubo
3
1.1k
業界横断 副業・兼業者の実態調査
fkske
0
160
Pix2Poly: A Sequence Prediction Method for End-to-end Polygonal Building Footprint Extraction from Remote Sensing Imagery
satai
3
480
生成的推薦の人気バイアスの分析:暗記の観点から / JSAI2025
upura
0
190
ウッドスタックチャン:木材を用いた小型エージェントロボットの開発と印象評価 / ec75-sato
yumulab
1
410
Featured
See All Featured
Speed Design
sergeychernyshev
32
1k
Exploring the Power of Turbo Streams & Action Cable | RailsConf2023
kevinliebholz
34
5.9k
Why You Should Never Use an ORM
jnunemaker
PRO
58
9.4k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
46
9.6k
How to Think Like a Performance Engineer
csswizardry
24
1.7k
Reflections from 52 weeks, 52 projects
jeffersonlam
351
20k
KATA
mclloyd
30
14k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
2.9k
Gamification - CAS2011
davidbonilla
81
5.3k
A better future with KSS
kneath
239
17k
For a Future-Friendly Web
brad_frost
179
9.8k
Testing 201, or: Great Expectations
jmmastey
42
7.6k
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
• •
• •
•
• • •
• • • •
• • • • •
• •
• •
• •
•
• • • •