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
220
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
180
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
150
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
160
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
140
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
270
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
330
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
220
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
210
Other Decks in Research
See All in Research
Computational OT #4 - Gradient flow and diffusion models
gpeyre
0
290
Transparency to sustain open science infrastructure - Printemps Couperin
mlarrieu
1
170
Principled AI ~深層学習時代における課題解決の方法論~
taniai
3
1.2k
When Submarine Cables Go Dark: Examining the Web Services Resilience Amid Global Internet Disruptions
irvin
0
190
大規模な2値整数計画問題に対する 効率的な重み付き局所探索法
mickey_kubo
1
220
チャッドローン:LLMによる画像認識を用いた自律型ドローンシステムの開発と実験 / ec75-morisaki
yumulab
1
430
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
250
数理最適化に基づく制御
mickey_kubo
5
660
Creation and environmental applications of 15-year daily inundation and vegetation maps for Siberia by integrating satellite and meteorological datasets
satai
3
100
研究テーマのデザインと研究遂行の方法論
hisashiishihara
5
1.4k
近似動的計画入門
mickey_kubo
4
960
Scale-Aware Recognition in Satellite images Under Resource Constraints
satai
3
330
Featured
See All Featured
Building Better People: How to give real-time feedback that sticks.
wjessup
367
19k
Bash Introduction
62gerente
614
210k
Building Adaptive Systems
keathley
43
2.6k
Fashionably flexible responsive web design (full day workshop)
malarkey
407
66k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
10
920
Building an army of robots
kneath
306
45k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
507
140k
Producing Creativity
orderedlist
PRO
346
40k
Testing 201, or: Great Expectations
jmmastey
42
7.5k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
48
5.4k
Intergalactic Javascript Robots from Outer Space
tanoku
271
27k
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)
• • • • •