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
250
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
文献紹介: Decomposable Neural Paraphrase Generation
2019/07/23の文献紹介で発表
Yumeto Inaoka
July 23, 2019
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
220
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
290
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
190
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
210
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
210
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
320
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
430
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
280
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
240
Other Decks in Research
See All in Research
nlp2026 In-Context Learningに基づく経路案内のための地理的知識の活用方法に関する検討
takashiinui
0
110
Overview of AGRODEP Activities and Current Status: Dr. Seraphin Niyonsenga
akademiya2063
PRO
0
120
Research Engineerという仕事 / Research Engineering: Bridging Research and Business
chck
1
240
kintone リサーチ副部/UXリサーチャー 業務紹介
cybozuinsideout
PRO
0
120
言語モデルから言語について語る際に押さえておきたいこと
eumesy
PRO
6
2.5k
COMETAを用いたデータ民主化運動の歴史
sazimai
0
130
Dual Quadric表現を用いた動的物体追跡とRGB-D・IMU制約の密結合によるオドメトリ推定
nanoshimarobot
0
450
長時間動画QAにおけるマルチエージェント推論 ・SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
murakawatakuya
1
160
オーストリア流 都市の公共交通サービス水準評価@公共交通オープンデータ最前線2026
trafficbrain
0
210
Ghost in the 7‑Zip: The Shadow of Residential Proxies Creeping into Your Life
nttcom
0
1.6k
NII S. Koyama's Lab Research Overview AY2026
skoyamalab
0
440
NLP colloquium: AI Safety Survey
kanekomasahiro
0
860
Featured
See All Featured
Crafting Experiences
bethany
1
230
Mobile First: as difficult as doing things right
swwweet
225
10k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
47
8.2k
How to make the Groovebox
asonas
2
2.3k
GitHub's CSS Performance
jonrohan
1033
470k
Utilizing Notion as your number one productivity tool
mfonobong
4
450
HDC tutorial
michielstock
2
750
The browser strikes back
jonoalderson
0
1.4k
Chasing Engaging Ingredients in Design
codingconduct
0
240
How to Ace a Technical Interview
jacobian
281
24k
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
270
[RailsConf 2023] Rails as a piece of cake
palkan
59
6.8k
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)
• • • • •