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
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Yumeto Inaoka
July 23, 2019
Research
250
0
Share
文献紹介: Decomposable Neural Paraphrase Generation
2019/07/23の文献紹介で発表
Yumeto Inaoka
July 23, 2019
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
210
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
270
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
180
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
200
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
190
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
310
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
390
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
260
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
230
Other Decks in Research
See All in Research
FUSE-RSVLM: Feature Fusion Vision-Language Model for Remote Sensing
satai
3
310
競合や要望に流されない─B2B SaaSでミニマム要件を決めるリアルな取り組み / Don't be swayed by competitors or requests - A real effort to determine minimum requirements for B2B SaaS
kaminashi
0
1.2k
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
350
一般道の交通量減少と速度低下についての全国分析と熊本市におけるケーススタディ(20251122 土木計画学研究発表会)
trafficbrain
0
190
LiDARセキュリティ最前線(2025年)
kentaroy47
0
390
生成AI による論文執筆サポート・ワークショップ データ分析/論文ドラフト編 / Generative AI-Assisted Paper Writing Support Workshop: Data Analysis and Drafting Edition
ks91
PRO
0
120
2026年1月の生成AI領域の重要リリース&トピック解説
kajikent
0
900
Dwangoでの漫画データ活用〜漫画理解と動画作成〜@コミック工学シンポジウム2025
kzmssk
0
200
都市交通マスタープランとその後への期待@熊本商工会議所・熊本経済同友会
trafficbrain
0
180
COFFEE-Japan PROJECT Impact Report(海ノ向こうコーヒー)
ontheslope
0
1.2k
学習型データ構造:機械学習を内包する新しいデータ構造の設計と解析
matsui_528
6
4.4k
業界横断 副業コンプライアンス調査 三者(副業者・本業先・発注者)におけるトラブル認知ギャップの構造分析
fkske
0
1.2k
Featured
See All Featured
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
4.2k
Measuring & Analyzing Core Web Vitals
bluesmoon
9
800
Leo the Paperboy
mayatellez
6
1.6k
Mind Mapping
helmedeiros
PRO
1
140
Deep Space Network (abreviated)
tonyrice
0
99
Automating Front-end Workflow
addyosmani
1370
200k
Context Engineering - Making Every Token Count
addyosmani
9
790
Paper Plane (Part 1)
katiecoart
PRO
0
6.3k
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
2
3.8k
Skip the Path - Find Your Career Trail
mkilby
1
93
The innovator’s Mindset - Leading Through an Era of Exponential Change - McGill University 2025
jdejongh
PRO
1
140
Building Adaptive Systems
keathley
44
3k
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)
• • • • •