Lock in $30 Savings on PRO—Offer Ends Soon! ⏳
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
文献紹介: Decomposable Neural Paraphrase Generation
Search
Yumeto Inaoka
July 23, 2019
Research
0
240
文献紹介: Decomposable Neural Paraphrase Generation
2019/07/23の文献紹介で発表
Yumeto Inaoka
July 23, 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
200
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
250
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
170
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
180
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
170
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
290
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
360
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
240
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
230
Other Decks in Research
See All in Research
SREはサイバネティクスの夢をみるか? / Do SREs Dream of Cybernetics?
yuukit
2
220
Stealing LUKS Keys via TPM and UUID Spoofing in 10 Minutes - BSides 2025
anykeyshik
0
170
POI: Proof of Identity
katsyoshi
0
120
若手研究者が国際会議(例えばIROS)でワークショップを企画するメリットと成功法!
tanichu
0
120
論文紹介:Safety Alignment Should be Made More Than Just a Few Tokens Deep
kazutoshishinoda
0
150
Open Gateway 5GC利用への期待と不安
stellarcraft
2
170
Earth AI: Unlocking Geospatial Insights with Foundation Models and Cross-Modal Reasoning
satai
2
150
生成AI による論文執筆サポート・ワークショップ ─ サーベイ/リサーチクエスチョン編 / Workshop on AI-Assisted Paper Writing Support: Survey/Research Question Edition
ks91
PRO
0
120
Agentic AI Era におけるサプライチェーン最適化
mickey_kubo
0
110
AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
satai
3
560
長期・短期メモリを活用したエージェントの個別最適化
isidaitc
0
340
J-RAGBench: 日本語RAGにおける Generator評価ベンチマークの構築
koki_itai
0
1.1k
Featured
See All Featured
How Software Deployment tools have changed in the past 20 years
geshan
0
29k
Evolving SEO for Evolving Search Engines
ryanjones
0
72
Lightning talk: Run Django tests with GitHub Actions
sabderemane
0
87
Exploring anti-patterns in Rails
aemeredith
2
200
エンジニアに許された特別な時間の終わり
watany
105
220k
Are puppies a ranking factor?
jonoalderson
0
2.3k
JAMstack: Web Apps at Ludicrous Speed - All Things Open 2022
reverentgeek
1
290
Avoiding the “Bad Training, Faster” Trap in the Age of AI
tmiket
0
34
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
Agile Actions for Facilitating Distributed Teams - ADO2019
mkilby
0
86
The Director’s Chair: Orchestrating AI for Truly Effective Learning
tmiket
0
60
The Spectacular Lies of Maps
axbom
PRO
1
400
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)
• • • • •