Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Speaker Deck
PRO
Sign in
Sign up for free
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
Yumeto Inaoka
August 08, 2019
Research
0
180
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
71
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
96
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
75
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
78
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
51
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
150
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
120
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
130
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
100
Other Decks in Research
See All in Research
世界観を考察するのが好き?Sound Horizonはいいぞ / Introduction to Sound Horizon
hyuyukun
0
790
メタバースプラットフォームを支えるアーキテクチャの現在とこれから
clustervr
PRO
0
530
OpenPack Challenge 2022 - チュートリアル (日本語)
getty708
0
130
Semantic Shift Stability: Efficient Way to Detect Performance Degradation of Word Embeddings and Pre-trained Language Models
upura
0
830
ランダム行列から深層学習へ
clustervr
PRO
0
490
第18回チャンピオンズミーティング・ライブラ杯ラウンド2集計 / Umamusume Libra 2022 Round2
kitachan_black
0
820
[輪講資料] Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space
hpprc
0
880
データ分析の進め方とニュースメディアでのデータ活用事例 / data-analysis-in-kaggle-and-news-media
upura
0
490
ログ収集入門Elastic_Searchの機能と活用事例
o_hasegawa
0
170
[CFML勉強会#7] EconMLに実装されている異質処置効果の推定手法の紹介・再考
fullflu
0
420
ベイズ能動学習による統計的実験計画~ベイズ最適化・能動的レベル集合推定の基礎と応用~
mayumichqm
0
230
フィッシング対策セミナー2022講演資料 / antiphishing-seminar2022-hasegawa
ayakohasegawa
0
1k
Featured
See All Featured
Reflections from 52 weeks, 52 projects
jeffersonlam
339
18k
Producing Creativity
orderedlist
PRO
335
38k
jQuery: Nuts, Bolts and Bling
dougneiner
57
6.6k
Three Pipe Problems
jasonvnalue
89
8.9k
VelocityConf: Rendering Performance Case Studies
addyosmani
317
22k
Infographics Made Easy
chrislema
235
17k
Imperfection Machines: The Place of Print at Facebook
scottboms
254
12k
Automating Front-end Workflow
addyosmani
1351
200k
KATA
mclloyd
12
9.7k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
31
20k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
7
590
Building Applications with DynamoDB
mza
85
5k
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
• •
• •
•
• • •
• • • •
• • • • •
• •
• •
• •
•
• • • •