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
230
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
340
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
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
150
Delta Airlines® Customer Care in the U.S.: How to Reach Them Now
bookingcomcustomersupportusa
0
110
A multimodal data fusion model for accurate and interpretable urban land use mapping with uncertainty analysis
satai
3
270
ストレス計測方法の確立に向けたマルチモーダルデータの活用
yurikomium
0
1.2k
Minimax and Bayes Optimal Best-arm Identification: Adaptive Experimental Design for Treatment Choice
masakat0
0
160
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
shunk031
14
9.7k
Creation and environmental applications of 15-year daily inundation and vegetation maps for Siberia by integrating satellite and meteorological datasets
satai
3
220
20250605_新交通システム推進議連_熊本都市圏「車1割削減、渋滞半減、公共交通2倍」から考える地方都市交通政策
trafficbrain
0
720
SSII2025 [TS2] リモートセンシング画像処理の最前線
ssii
PRO
7
3k
数理最適化と機械学習の融合
mickey_kubo
16
9.2k
心理言語学の視点から再考する言語モデルの学習過程
chemical_tree
2
550
数理最適化に基づく制御
mickey_kubo
6
720
Featured
See All Featured
A Modern Web Designer's Workflow
chriscoyier
696
190k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
Docker and Python
trallard
45
3.5k
Music & Morning Musume
bryan
46
6.8k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
139
34k
The Power of CSS Pseudo Elements
geoffreycrofte
77
5.9k
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
8
490
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
44
2.5k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
126
53k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
Navigating Team Friction
lara
189
15k
Improving Core Web Vitals using Speculation Rules API
sergeychernyshev
18
1.1k
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)
• • • • •