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
230
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
190
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
240
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
160
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
180
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
160
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
280
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
350
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
230
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
220
Other Decks in Research
See All in Research
AIスパコン「さくらONE」のLLM学習ベンチマークによる性能評価 / SAKURAONE LLM Training Benchmarking
yuukit
2
780
情報技術の社会実装に向けた応用と課題:ニュースメディアの事例から / appmech-jsce 2025
upura
0
240
LLM-jp-3 and beyond: Training Large Language Models
odashi
1
540
「どう育てるか」より「どう働きたいか」〜スクラムマスターの最初の一歩〜
hirakawa51
0
990
Vision and LanguageからのEmbodied AIとAI for Science
yushiku
PRO
1
570
A scalable, annual aboveground biomass product for monitoring carbon impacts of ecosystem restoration projects
satai
4
410
若手研究者が国際会議(例えばIROS)でワークショップを企画するメリットと成功法!
tanichu
0
100
多言語カスタマーインタビューの“壁”を越える~PMと生成AIの共創~ 株式会社ジグザグ 松野 亘
watarumatsuno
0
140
EcoWikiRS: Learning Ecological Representation of Satellite Images from Weak Supervision with Species Observation and Wikipedia
satai
3
310
世界の人気アプリ100個を分析して見えたペイウォール設計の心得
akihiro_kokubo
PRO
63
33k
大学見本市2025 JSTさきがけ事業セミナー「顔の見えないセンシング技術:多様なセンサにもとづく個人情報に配慮した人物状態推定」
miso2024
0
170
Time to Cash: The Full Stack Breakdown of Modern ATM Attacks
ratatata
0
160
Featured
See All Featured
Done Done
chrislema
186
16k
A designer walks into a library…
pauljervisheath
209
24k
Testing 201, or: Great Expectations
jmmastey
46
7.7k
The World Runs on Bad Software
bkeepers
PRO
72
11k
The Straight Up "How To Draw Better" Workshop
denniskardys
239
140k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
48
9.7k
Optimising Largest Contentful Paint
csswizardry
37
3.5k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
46
7.8k
Gamification - CAS2011
davidbonilla
81
5.5k
Practical Orchestrator
shlominoach
190
11k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
9.7k
Code Reviewing Like a Champion
maltzj
526
40k
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)
• • • • •