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: Decomposable Neural Paraphrase Generation
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Yumeto Inaoka
July 23, 2019
Research
250
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
文献紹介: Decomposable Neural Paraphrase Generation
2019/07/23の文献紹介で発表
Yumeto Inaoka
July 23, 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
220
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
280
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
210
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
210
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
320
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
420
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
280
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
240
Other Decks in Research
See All in Research
Can We Teach Logical Reasoning to LLMs? – An Approach Using Synthetic Corpora (AAAI 2026 bridge keynote)
morishtr
1
250
National high-resolution cropland classification of Japan with agricultural census information and multi-temporal multi-modality datasets
satai
3
290
定数整数除算・剰余算最適化再考
herumi
1
120
Scalable dynamic origin-destination demand estimation enhanced by high-resolution satellite imagery data
satai
3
270
SOTAのさらに先へ:厳しい推論制約下での高性能モデルのPost-Training
analokmaus
0
1.2k
老舗ものづくり企業でリサーチが変革を起こすまで - 三菱重工DXの実践
skydats
0
180
「車1割削減、渋滞半減、公共交通2倍」を 熊本から岡山へ@RACDA設立30周年記念都市交通フォーラム2026
trafficbrain
1
1.2k
LINEヤフー データサイエンス Meetup「三井物産コモディティ予測チャレンジ」の舞台裏-AlpacaTechパート
gamella
1
570
[チュートリアル] 電波マップ構築入門 :研究動向と課題設定の勘所
k_sato
0
480
LOSの検討(λ Kansai 2026 in Winter)
motopu
0
140
通時的な類似度行列に基づく単語の意味変化の分析
rudorudo11
0
310
さくらインターネット研究所テックトーク2026春、研究開発Gr.25年度成果26年度方針
kikuzo
0
150
Featured
See All Featured
A Guide to Academic Writing Using Generative AI - A Workshop
ks91
PRO
1
320
<Decoding/> the Language of Devs - We Love SEO 2024
nikkihalliwell
1
240
The World Runs on Bad Software
bkeepers
PRO
72
12k
Groundhog Day: Seeking Process in Gaming for Health
codingconduct
0
200
SEO for Brand Visibility & Recognition
aleyda
0
4.6k
Music & Morning Musume
bryan
47
7.2k
Believing is Seeing
oripsolob
1
140
How Software Deployment tools have changed in the past 20 years
geshan
0
34k
Bash Introduction
62gerente
615
220k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
28
3.5k
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
soudai
PRO
65
55k
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
mfonobong
2
430
Transcript
Decomposable Neural Paraphrase Generation
https://arxiv.org/abs/1906.09741
• • • •
• • •
•
• • •
• • •
• •
• • = [1 , … , ] • =
[1 , … , ]
• • • ℎ = BiLSTM( ; ℎ−1 , ℎ+1
) • = LSTM ℎ , −1 ; −1 • = GumbelSoftmax( , )
• • = − encoderz (, ) • 1:−1 ,
= − encoderz , 1:−1
• • 1:−1 , = σ 1:−1 , ( |1:−1
, )
• 0 , 1 • = LSTM 0 ; 1
; −1 ; −1 • 1:−1 , = GumbelSoftmax ,
• • ∗ = 0 ∗ = 1
• • ℒ = σ=1 log 1:−1 , + σ=1
log ∗ + σ=1 log ( ∗ 1:−1 ,
• • •
• •
•
• •
• •
• •
• •
• •
• • From 1(best) to 4(worst)
• • • • •