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
240
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
200
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
260
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
300
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
370
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
240
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
230
Other Decks in Research
See All in Research
Agentic AI フレームワーク戦略白書 (2025年度版)
mickey_kubo
1
110
Multi-Agent Large Language Models for Code Intelligence: Opportunities, Challenges, and Research Directions
fatemeh_fard
0
120
An Open and Reproducible Deep Research Agent for Long-Form Question Answering
ikuyamada
0
210
POI: Proof of Identity
katsyoshi
0
130
CoRL2025速報
rpc
4
3.9k
ウェブ・ソーシャルメディア論文読み会 第36回: The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents (EMNLP, 2025)
hkefka385
0
130
GPUを利用したStein Particle Filterによる点群6自由度モンテカルロSLAM
takuminakao
0
840
データサイエンティストをめぐる環境の違い2025年版〈一般ビジネスパーソン調査の国際比較〉
datascientistsociety
PRO
0
530
Agentic AI Era におけるサプライチェーン最適化
mickey_kubo
0
120
Remote sensing × Multi-modal meta survey
satai
4
680
20年前に50代だった人たちの今
hysmrk
0
130
AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
satai
3
720
Featured
See All Featured
New Earth Scene 8
popppiees
1
1.4k
The Mindset for Success: Future Career Progression
greggifford
PRO
0
220
The Pragmatic Product Professional
lauravandoore
37
7.1k
The World Runs on Bad Software
bkeepers
PRO
72
12k
ラッコキーワード サービス紹介資料
rakko
0
2M
Into the Great Unknown - MozCon
thekraken
40
2.2k
Producing Creativity
orderedlist
PRO
348
40k
GitHub's CSS Performance
jonrohan
1032
470k
Being A Developer After 40
akosma
91
590k
Designing for humans not robots
tammielis
254
26k
Exploring the relationship between traditional SERPs and Gen AI search
raygrieselhuber
PRO
2
3.5k
Introduction to Domain-Driven Design and Collaborative software design
baasie
1
560
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)
• • • • •