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
130
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
250
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
210
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
200
Other Decks in Research
See All in Research
インドネシアのQA事情を紹介するの
yujijs
0
190
VAGeo: View-specific Attention for Cross-View Object Geo-Localization
satai
3
230
NLP2025 WS Shared Task 文法誤り訂正部門 ehiMetrick
sugiyamaseiji
0
170
Introduction of NII S. Koyama's Lab (AY2025)
skoyamalab
0
310
A Segment Anything Model based weakly supervised learning method for crop mapping using Sentinel-2 time series images
satai
3
310
TRIPOD+AI Expandedチェックリスト 有志翻訳による日本語版 version.1.1
shuntaros
0
130
DeepSeek を利用する上でのリスクと安全性の考え方
schroneko
3
1.4k
Adaptive fusion of multi-modal remote sensing data for optimal sub-field crop yield prediction
satai
3
140
小ねぎ調製位置検出のためのインスタンスセグメンテーション
takuto_andtt
0
120
Collaborative Development of Foundation Models at Japanese Academia
odashi
2
540
プロシェアリング白書2025_PROSHARING_REPORT_2025
circulation
1
620
ラムダ計算の拡張に基づく 音楽プログラミング言語mimium とそのVMの実装
tomoyanonymous
0
450
Featured
See All Featured
XXLCSS - How to scale CSS and keep your sanity
sugarenia
248
1.3M
Building a Modern Day E-commerce SEO Strategy
aleyda
40
7.2k
Thoughts on Productivity
jonyablonski
69
4.6k
Scaling GitHub
holman
459
140k
Build The Right Thing And Hit Your Dates
maggiecrowley
35
2.7k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
48
5.4k
Reflections from 52 weeks, 52 projects
jeffersonlam
349
20k
Art, The Web, and Tiny UX
lynnandtonic
298
20k
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
29
2.6k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
13
840
The Cost Of JavaScript in 2023
addyosmani
49
7.8k
Unsuck your backbone
ammeep
671
58k
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)
• • • • •