$30 off During Our Annual Pro Sale. View Details »
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
When Learned Data Structures Meet Computer Vision
matsui_528
1
1.5k
Multi-Agent Large Language Models for Code Intelligence: Opportunities, Challenges, and Research Directions
fatemeh_fard
0
110
まずはここから:Overleaf共同執筆・CopilotでAIコーディング入門・Codespacesで独立環境
matsui_528
2
920
EcoWikiRS: Learning Ecological Representation of Satellite Images from Weak Supervision with Species Observation and Wikipedia
satai
3
460
空間音響処理における物理法則に基づく機械学習
skoyamalab
0
130
SREはサイバネティクスの夢をみるか? / Do SREs Dream of Cybernetics?
yuukit
2
220
SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing
satai
3
190
その推薦システムの評価指標、ユーザーの感覚とズレてるかも
kuri8ive
1
280
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
地域丸ごとデイサービス「Go トレ」の紹介
smartfukushilab1
0
660
Time to Cash: The Full Stack Breakdown of Modern ATM Attacks
ratatata
0
180
論文紹介:Not All Tokens Are What You Need for Pretraining
kosuken
1
220
Featured
See All Featured
ReactJS: Keep Simple. Everything can be a component!
pedronauck
666
130k
Introduction to Domain-Driven Design and Collaborative software design
baasie
1
500
Leading Effective Engineering Teams in the AI Era
addyosmani
9
1.4k
4 Signs Your Business is Dying
shpigford
186
22k
Agile Actions for Facilitating Distributed Teams - ADO2019
mkilby
0
86
Building Flexible Design Systems
yeseniaperezcruz
330
39k
Skip the Path - Find Your Career Trail
mkilby
0
23
A Modern Web Designer's Workflow
chriscoyier
698
190k
Why You Should Never Use an ORM
jnunemaker
PRO
61
9.6k
Visualization
eitanlees
150
16k
How Software Deployment tools have changed in the past 20 years
geshan
0
29k
Building Applications with DynamoDB
mza
96
6.8k
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)
• • • • •