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
220
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
170
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
220
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
150
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
160
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
140
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
260
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
320
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
220
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
210
Other Decks in Research
See All in Research
90 分で学ぶ P 対 NP 問題
e869120
16
7.2k
SSII2025 [SS2] 横浜DeNAベイスターズの躍進を支えたAIプロダクト
ssii
PRO
6
3.1k
Computational OT #1 - Monge and Kantorovitch
gpeyre
0
150
Mathematics in the Age of AI and the 4 Generation University
hachama
0
150
学生向けアンケート<データサイエンティストについて>
datascientistsociety
PRO
0
1.9k
Mechanistic Interpretability:解釈可能性研究の新たな潮流
koshiro_aoki
1
130
[輪講] SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
nk35jk
2
250
NLP2025 WS Shared Task 文法誤り訂正部門 ehiMetrick
sugiyamaseiji
0
180
データxデジタルマップで拓く ミラノ発・地域共創最前線
mapconcierge4agu
0
160
数理最適化に基づく制御
mickey_kubo
5
630
Weekly AI Agents News!
masatoto
33
66k
JSAI NeurIPS 2024 参加報告会(AI アライメント)
akifumi_wachi
5
1k
Featured
See All Featured
Understanding Cognitive Biases in Performance Measurement
bluesmoon
29
1.7k
Adopting Sorbet at Scale
ufuk
76
9.4k
How to Think Like a Performance Engineer
csswizardry
23
1.6k
Designing Experiences People Love
moore
142
24k
Agile that works and the tools we love
rasmusluckow
329
21k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
160
15k
Product Roadmaps are Hard
iamctodd
PRO
53
11k
What's in a price? How to price your products and services
michaelherold
245
12k
Facilitating Awesome Meetings
lara
54
6.4k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
32
2.3k
We Have a Design System, Now What?
morganepeng
52
7.6k
Git: the NoSQL Database
bkeepers
PRO
430
65k
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)
• • • • •