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
0
250
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
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
190
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
180
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
380
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
[Devfest Incheon 2025] 모두를 위한 친절한 언어모델(LLM) 학습 가이드
beomi
2
1.5k
AI Agentの精度改善に見るML開発との共通点 / commonalities in accuracy improvements in agentic era
shimacos
5
1.3k
Collective Predictive Coding and World Models in LLMs: A System 0/1/2/3 Perspective on Hierarchical Physical AI (IEEE SII 2026 Plenary Talk)
tanichu
1
270
Upgrading Multi-Agent Pathfinding for the Real World
kei18
0
320
Akamaiのキャッシュ効率を支えるAdaptSizeについての論文を読んでみた
bootjp
1
480
SREはサイバネティクスの夢をみるか? / Do SREs Dream of Cybernetics?
yuukit
3
420
生成的情報検索時代におけるAI利用と認知バイアス
trycycle
PRO
0
340
財務諸表監査のための逐次検定
masakat0
1
270
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
170
LLM-jp-3 and beyond: Training Large Language Models
odashi
1
780
"主観で終わらせない"定性データ活用 ― プロダクトディスカバリーを加速させるインサイトマネジメント / Utilizing qualitative data that "doesn't end with subjectivity" - Insight management that accelerates product discovery
kaminashi
15
22k
COFFEE-Japan PROJECT Impact Report(海ノ向こうコーヒー)
ontheslope
0
750
Featured
See All Featured
Docker and Python
trallard
47
3.7k
The Language of Interfaces
destraynor
162
26k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
231
22k
The #1 spot is gone: here's how to win anyway
tamaranovitovic
2
970
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
26
3.4k
Jamie Indigo - Trashchat’s Guide to Black Boxes: Technical SEO Tactics for LLMs
techseoconnect
PRO
0
78
GraphQLの誤解/rethinking-graphql
sonatard
75
11k
Lightning Talk: Beautiful Slides for Beginners
inesmontani
PRO
1
460
How Fast Is Fast Enough? [PerfNow 2025]
tammyeverts
3
470
The Art of Programming - Codeland 2020
erikaheidi
57
14k
SEO Brein meetup: CTRL+C is not how to scale international SEO
lindahogenes
0
2.4k
Designing Experiences People Love
moore
144
24k
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)
• • • • •