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
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
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
220
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
280
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
210
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
210
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
430
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
280
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
240
Other Decks in Research
See All in Research
適応的スパムフィルタのための軽量な類似メッセージカウンタ / jsai2026-adaptive-spam-filter
monochromegane
0
4.2k
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
shunk031
4
1.1k
Visual SLAM未来予測 / Future Prediction in Visual SLAM
koide3
1
540
「なんとなく」の顧客理解から脱却する ──顧客の解像度を武器にするインサイトマネジメント
tajima_kaho
11
8.6k
はじまりの クエスチョンブック —余暇と豊かさにあふれた社会とは?
culturaltransition
PRO
0
550
論文紹介:HalluCitation Matters
wasyro
0
120
「AIとWhyを深堀る」をAIと深堀る
iflection
0
510
進学校の生徒にはア行の苗字が多いのか
ozekinote
0
470
AGI4OPT:自然言語から数理最適化を導くエ ージェントスキル Translating Human Intent into Mathematical Optimization
mickey_kubo
0
150
GLIM とMegaParticles:正規分布近似の限界とタイトカップリング&パーティクルフィルタの進展 / GLIM and MegaParticles : Progress of the distribution representation in SLAM
koide3
0
520
研究室単位での自律的 IPv6接続性確立に向けたAS共同運用モデルの提案と実証
reokashiwa
PRO
0
140
LLM の Attention 機構まとめ — 数式・計算量・メモリ
puwaer
8
2.2k
Featured
See All Featured
GraphQLとの向き合い方2022年版
quramy
50
15k
How to optimise 3,500 product descriptions for ecommerce in one day using ChatGPT
katarinadahlin
PRO
1
3.7k
Tell your own story through comics
letsgokoyo
1
990
Scaling GitHub
holman
464
140k
Building Applications with DynamoDB
mza
96
7.1k
Breaking role norms: Why Content Design is so much more than writing copy - Taylor Woolridge
uxyall
0
340
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.6k
Navigating the Design Leadership Dip - Product Design Week Design Leaders+ Conference 2024
apolaine
1
370
Leveraging LLMs for student feedback in introductory data science courses - posit::conf(2025)
minecr
1
310
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
450
Bootstrapping a Software Product
garrettdimon
PRO
307
120k
Ruling the World: When Life Gets Gamed
codingconduct
0
280
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)
• • • • •