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
170
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
まずはここから:Overleaf共同執筆・CopilotでAIコーディング入門・Codespacesで独立環境
matsui_528
2
590
電通総研の生成AI・エージェントの取り組みエンジニアリング業務向けAI活用事例紹介
isidaitc
1
1k
時系列データに対する解釈可能な 決定木クラスタリング
mickey_kubo
2
1k
EarthSynth: Generating Informative Earth Observation with Diffusion Models
satai
3
360
Language Models Are Implicitly Continuous
eumesy
PRO
0
290
スキマバイトサービスにおける現場起点でのデザインアプローチ
yoshioshingyouji
0
240
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
200
EarthDial: Turning Multi-sensory Earth Observations to Interactive Dialogues
satai
3
220
日本語新聞記事を用いた大規模言語モデルの暗記定量化 / LLMC2025
upura
0
240
言語モデルの地図:確率分布と情報幾何による類似性の可視化
shimosan
6
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
130
Towards a More Efficient Reasoning LLM: AIMO2 Solution Summary and Introduction to Fast-Math Models
analokmaus
2
880
Featured
See All Featured
Practical Orchestrator
shlominoach
190
11k
Building a Modern Day E-commerce SEO Strategy
aleyda
43
7.7k
Embracing the Ebb and Flow
colly
88
4.8k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
53k
Raft: Consensus for Rubyists
vanstee
139
7.1k
How GitHub (no longer) Works
holman
315
140k
How to Ace a Technical Interview
jacobian
280
24k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
285
14k
Context Engineering - Making Every Token Count
addyosmani
5
200
ReactJS: Keep Simple. Everything can be a component!
pedronauck
667
120k
Testing 201, or: Great Expectations
jmmastey
45
7.7k
jQuery: Nuts, Bolts and Bling
dougneiner
64
7.9k
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)
• • • • •