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
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
300
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
Attaques quantiques sur Bitcoin : comment se protéger ?
rlifchitz
0
110
Tiaccoon: Unified Access Control with Multiple Transports in Container Networks
hiroyaonoe
0
270
音声感情認識技術の進展と展望
nagase
0
420
[論文紹介] Intuitive Fine-Tuning
ryou0634
0
160
snlp2025_prevent_llm_spikes
takase
0
420
超高速データサイエンス
matsui_528
1
330
さまざまなAgent FrameworkとAIエージェントの評価
ymd65536
1
380
AIグラフィックデザインの進化:断片から統合(One Piece)へ / From Fragment to One Piece: A Survey on AI-Driven Graphic Design
shunk031
0
580
Thirty Years of Progress in Speech Synthesis: A Personal Perspective on the Past, Present, and Future
ktokuda
0
140
ForestCast: Forecasting Deforestation Risk at Scale with Deep Learning
satai
2
180
国際論文を出そう!ICRA / IROS / RA-L への論文投稿の心構えとノウハウ / RSJ2025 Luncheon Seminar
koide3
12
6.6k
Remote sensing × Multi-modal meta survey
satai
4
670
Featured
See All Featured
AI Search: Implications for SEO and How to Move Forward - #ShenzhenSEOConference
aleyda
1
1k
Navigating Team Friction
lara
191
16k
Designing for Timeless Needs
cassininazir
0
110
Efficient Content Optimization with Google Search Console & Apps Script
katarinadahlin
PRO
0
260
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
52
5.8k
Being A Developer After 40
akosma
91
590k
Why Our Code Smells
bkeepers
PRO
340
58k
Documentation Writing (for coders)
carmenintech
77
5.2k
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
2
3.5k
[RailsConf 2023] Rails as a piece of cake
palkan
58
6.2k
Exploring anti-patterns in Rails
aemeredith
2
220
It's Worth the Effort
3n
187
29k
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)
• • • • •