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
270
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
120
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
160
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
120
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
120
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
89
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
210
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
180
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
170
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
180
Other Decks in Research
See All in Research
marukotenant01/tenant-20240826
marketing2024
0
510
TransformerによるBEV Perception
hf149
1
310
ニューラルネットワークの損失地形
joisino
PRO
33
15k
日本語医療LLM評価ベンチマークの構築と性能分析
fta98
3
520
論文読み会 SNLP2024 Instruction-tuned Language Models are Better Knowledge Learners. In: ACL 2024
s_mizuki_nlp
1
330
Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve
eumesy
PRO
6
1.1k
20240918 交通くまもとーく 未来の鉄道網編(太田恒平)
trafficbrain
0
150
Как стать 10x экспертом
ikurochkin
1
170
クラウドソーシングによる学習データ作成と品質管理(セキュリティキャンプ2024全国大会D2講義資料)
takumi1001
0
220
「確率的なオウム」にできること、またそれがなぜできるのかについて
eumesy
PRO
7
3k
RSJ2024「基盤モデルの実ロボット応用」チュートリアルA(河原塚)
haraduka
2
610
「Goトレ」のご紹介
smartfukushilab1
0
710
Featured
See All Featured
jQuery: Nuts, Bolts and Bling
dougneiner
61
7.5k
Build The Right Thing And Hit Your Dates
maggiecrowley
32
2.3k
What’s in a name? Adding method to the madness
productmarketing
PRO
22
3.1k
Into the Great Unknown - MozCon
thekraken
31
1.4k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
27
740
Become a Pro
speakerdeck
PRO
24
4.9k
The Invisible Side of Design
smashingmag
297
50k
Learning to Love Humans: Emotional Interface Design
aarron
272
40k
Java REST API Framework Comparison - PWX 2021
mraible
PRO
28
7.8k
Designing on Purpose - Digital PM Summit 2013
jponch
114
6.9k
Optimizing for Happiness
mojombo
376
69k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
26
2k
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
• •
• •
•
• • •
• • • •
• • • • •
• •
• •
• •
•
• • • •