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
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
190
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
320
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
270
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
240
Other Decks in Research
See All in Research
SoftMatcha 2: 1兆語規模コーパスの超高速かつ柔らかい検索
e869120_sub
6
3.2k
それ、チームの改善になってますか?ー「チームとは?」から始めた組織の実験ー
hirakawa51
0
1.1k
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
980
IEEE AIxVR 2026 Keynote Talk: "Beyond Visibility: Understanding Scenes and Humans under Challenging Conditions with Diverse Sensing"
miso2024
0
180
An Open and Reproducible Deep Research Agent for Long-Form Question Answering
ikuyamada
0
440
Model Discovery and Graph Simulation: A Lightweight Gateway to Chaos Engineering
anatolykr
0
150
COFFEE-Japan PROJECT Impact Report(海ノ向こうコーヒー)
ontheslope
0
1.5k
Ankylosing Spondylitis
ankh2054
0
170
東京大学工学部計数工学科、計数工学特別講義の説明資料
kikuzo
0
360
さくらインターネット研究所テックトーク2026春、研究開発Gr.25年度成果26年度方針
kikuzo
0
130
ブレグマン距離最小化に基づくリース表現量推定:バイアス除去学習の統一理論
masakat0
0
250
台湾モデルに学ぶ詐欺広告対策:市民参加の必要性
dd2030
0
310
Featured
See All Featured
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
9
1.3k
A Modern Web Designer's Workflow
chriscoyier
698
190k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
Joys of Absence: A Defence of Solitary Play
codingconduct
1
360
Primal Persuasion: How to Engage the Brain for Learning That Lasts
tmiket
0
330
<Decoding/> the Language of Devs - We Love SEO 2024
nikkihalliwell
1
210
How To Speak Unicorn (iThemes Webinar)
marktimemedia
1
450
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
How to make the Groovebox
asonas
2
2.2k
Evolving SEO for Evolving Search Engines
ryanjones
0
190
StorybookのUI Testing Handbookを読んだ
zakiyama
31
6.7k
JAMstack: Web Apps at Ludicrous Speed - All Things Open 2022
reverentgeek
1
430
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)
• • • • •