Upgrade to PRO for Only $50/Year—Limited-Time Offer! 🔥
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
250
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
170
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
170
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
290
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
360
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
「リアル×スキマ時間」を活用したUXリサーチ 〜新規事業を前に進めるためのUXリサーチプロセスの設計〜
techtekt
PRO
0
200
SkySense V2: A Unified Foundation Model for Multi-modal Remote Sensing
satai
3
220
第二言語習得研究における 明示的・暗示的知識の再検討:この分類は何に役に立つか,何に役に立たないか
tam07pb915
0
400
さまざまなAgent FrameworkとAIエージェントの評価
ymd65536
1
370
Thirty Years of Progress in Speech Synthesis: A Personal Perspective on the Past, Present, and Future
ktokuda
0
140
Multi-Agent Large Language Models for Code Intelligence: Opportunities, Challenges, and Research Directions
fatemeh_fard
0
120
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
210
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
65
35k
LLM-jp-3 and beyond: Training Large Language Models
odashi
1
720
病院向け生成AIプロダクト開発の実践と課題
hagino3000
0
480
Learning to (Learn at Test Time): RNNs with Expressive Hidden States
kurita
1
300
Tiaccoon: Unified Access Control with Multiple Transports in Container Networks
hiroyaonoe
0
190
Featured
See All Featured
The Cult of Friendly URLs
andyhume
79
6.7k
My Coaching Mixtape
mlcsv
0
13
Data-driven link building: lessons from a $708K investment (BrightonSEO talk)
szymonslowik
1
850
Typedesign – Prime Four
hannesfritz
42
2.9k
GitHub's CSS Performance
jonrohan
1032
470k
Applied NLP in the Age of Generative AI
inesmontani
PRO
3
2k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
Why Our Code Smells
bkeepers
PRO
340
57k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
508
140k
YesSQL, Process and Tooling at Scale
rocio
174
15k
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
65
35k
Public Speaking Without Barfing On Your Shoes - THAT 2023
reverentgeek
1
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)
• • • • •