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
260
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
290
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
200
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
220
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
330
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
440
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
300
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
250
Other Decks in Research
See All in Research
[最先端NLP勉強会2026] Checklists Are Better Than Reward Models For Aligning Language Models
nzw0301
1
310
2026年版中小企業白書・小規模企業白書の概要
ozekinote
0
210
CVPR2026論文紹介_VLMにとって良いvision encoderとは何か?Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance
kobayashi31
1
210
最先端NLP勉強会2026 論文紹介:Reasoning with Sampling: Your Base Model is Smarter Than You Think (ICLR 2026 paper)
kogoro
4
590
RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
satai
3
530
適応的スパムフィルタのための軽量な類似メッセージカウンタ / jsai2026-adaptive-spam-filter
monochromegane
0
5.3k
論文紹介: Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind
hisaokatsumi
0
160
ros2-perf-multihost: 分散システムにおける客観的なアーキテクチャ評価フレームワーク
takasehideki
0
250
20260624 NLP colloquium: 単一のhubテキストがCLIPを壊す:hubnessによる埋め込みの脆弱性特定
de9uch1
2
250
長時間動画QAにおけるマルチエージェント推論 ・SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
murakawatakuya
1
200
VLMの推論を高速化する視覚トークン削減の仕組み
tattaka
2
300
【中間報告】国会議員の立法・政策実務を支える環境を巡る現状と課題
polipoli
0
570
Featured
See All Featured
Pawsitive SEO: Lessons from My Dog (and Many Mistakes) on Thriving as a Consultant in the Age of AI
davidcarrasco
0
240
Measuring & Analyzing Core Web Vitals
bluesmoon
9
990
How to Think Like a Performance Engineer
csswizardry
28
2.8k
jQuery: Nuts, Bolts and Bling
dougneiner
66
8.6k
Mobile First: as difficult as doing things right
swwweet
225
10k
The Spectacular Lies of Maps
axbom
PRO
1
980
The Anti-SEO Checklist Checklist. Pubcon Cyber Week
ryanjones
0
230
How to build a perfect <img>
jonoalderson
1
6k
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
870
Darren the Foodie - Storyboard
khoart
PRO
3
3.9k
The untapped power of vector embeddings
frankvandijk
2
1.9k
Fantastic passwords and where to find them - at NoRuKo
philnash
52
3.8k
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)
• • • • •