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
250
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
230
Other Decks in Research
See All in Research
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
420
20年前に50代だった人たちの今
hysmrk
0
130
Aurora Serverless からAurora Serverless v2への課題と知見を論文から読み解く/Understanding the challenges and insights of moving from Aurora Serverless to Aurora Serverless v2 from a paper
bootjp
6
1.4k
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
140
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
110
離散凸解析に基づく予測付き離散最適化手法 (IBIS '25)
taihei_oki
PRO
1
670
Tiaccoon: Unified Access Control with Multiple Transports in Container Networks
hiroyaonoe
0
520
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
310
姫路市 -都市OSの「再実装」-
hopin
0
1.6k
ロボット学習における大規模検索技術の展開と応用
denkiwakame
1
200
2025-11-21-DA-10th-satellite
yegusa
0
110
SREはサイバネティクスの夢をみるか? / Do SREs Dream of Cybernetics?
yuukit
3
360
Featured
See All Featured
It's Worth the Effort
3n
188
29k
技術選定の審美眼(2025年版) / Understanding the Spiral of Technologies 2025 edition
twada
PRO
117
100k
[SF Ruby Conf 2025] Rails X
palkan
0
730
Building Better People: How to give real-time feedback that sticks.
wjessup
370
20k
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
mfonobong
2
270
B2B Lead Gen: Tactics, Traps & Triumph
marketingsoph
0
48
Practical Orchestrator
shlominoach
191
11k
Done Done
chrislema
186
16k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
359
30k
Producing Creativity
orderedlist
PRO
348
40k
Scaling GitHub
holman
464
140k
Into the Great Unknown - MozCon
thekraken
40
2.2k
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)
• • • • •