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
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
210
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
270
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
200
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
190
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
390
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
270
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
240
Other Decks in Research
See All in Research
進学校の生徒にはア行の苗字が多いのか
ozekinote
0
390
2026 東京科学大 情報通信系 研究室紹介 (大岡山)
icttitech
0
3.1k
LLM の Attention 機構まとめ — 数式・計算量・メモリ
puwaer
7
1.8k
svc-hook: hooking system calls on ARM64 by binary rewriting
retrage
2
240
R&Dチームを起ち上げる
shibuiwilliam
1
240
計算情報学研究室(数理情報学第7研究室)2026
tomohirokoana
0
280
データサイエンティストの業務変化
datascientistsociety
PRO
0
390
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
360
typst の使い方:言語学を研究する学生のために
gitomochang
0
400
2026 東京科学大 情報通信系 研究室紹介 (すずかけ台)
icttitech
0
3.2k
「行ける・行けない表」による地域公共交通の性能評価
bansousha
0
150
Tiaccoon: Unified Access Control with Multiple Transports in Container Networks
hiroyaonoe
0
1.6k
Featured
See All Featured
Un-Boring Meetings
codingconduct
0
280
So, you think you're a good person
axbom
PRO
2
2k
Sam Torres - BigQuery for SEOs
techseoconnect
PRO
0
260
Designing for Timeless Needs
cassininazir
0
220
Technical Leadership for Architectural Decision Making
baasie
3
360
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
162
16k
Discover your Explorer Soul
emna__ayadi
2
1.1k
The Invisible Side of Design
smashingmag
302
52k
Abbi's Birthday
coloredviolet
2
7.5k
More Than Pixels: Becoming A User Experience Designer
marktimemedia
3
400
Future Trends and Review - Lecture 12 - Web Technologies (1019888BNR)
signer
PRO
0
3.5k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
287
14k
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)
• • • • •