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
200
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
150
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
200
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
130
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
140
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
120
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
240
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
300
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
200
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
190
Other Decks in Research
See All in Research
渋谷Well-beingアンケート調査結果
shibuyasmartcityassociation
0
400
アプリケーションから知るモデルマージ
maguro27
0
260
PhD Defence: Considering Temporal and Contextual Information for Lexical Semantic Change Detection
a1da4
0
120
Optimal and Diffusion Transports in Machine Learning
gpeyre
0
1.2k
PetiteSRE_GenAIEraにおけるインフラのあり方観察
ichichi
0
270
Data-centric AI勉強会 「ロボットにおけるData-centric AI」
haraduka
0
470
打率7割を実現する、プロダクトディスカバリーの7つの極意(pmconf2024)
geshi0820
0
330
ダイナミックプライシング とその実例
skmr2348
3
600
Weekly AI Agents News! 1月号 アーカイブ
masatoto
1
180
DeepSeek-R1の論文から読み解く背景技術
personabb
3
320
eAI (Engineerable AI) プロジェクトの全体像 / Overview of eAI Project
ishikawafyu
0
380
サーブレシーブ成功率は勝敗に影響するか?
vball_panda
0
550
Featured
See All Featured
jQuery: Nuts, Bolts and Bling
dougneiner
63
7.7k
The Invisible Side of Design
smashingmag
299
50k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
10
1.3k
Code Review Best Practice
trishagee
67
18k
Scaling GitHub
holman
459
140k
A Modern Web Designer's Workflow
chriscoyier
693
190k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
233
17k
GraphQLの誤解/rethinking-graphql
sonatard
68
10k
Art, The Web, and Tiny UX
lynnandtonic
298
20k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
366
25k
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
129
19k
How to Create Impact in a Changing Tech Landscape [PerfNow 2023]
tammyeverts
49
2.3k
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)
• • • • •