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
180
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
130
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
170
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
120
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
120
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
93
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
210
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
270
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
180
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
yumeto
1
180
Other Decks in Research
See All in Research
大規模言語モデルを用いた日本語視覚言語モデルの評価方法とベースラインモデルの提案 【MIRU 2024】
kentosasaki
2
520
論文読み会 SNLP2024 Instruction-tuned Language Models are Better Knowledge Learners. In: ACL 2024
s_mizuki_nlp
1
350
論文紹介/Expectations over Unspoken Alternatives Predict Pragmatic Inferences
chemical_tree
1
260
ミニ四駆AI用制御装置の事例紹介
aks3g
0
160
第 2 部 11 章「大規模言語モデルの研究開発から実運用に向けて」に向けて / MLOps Book Chapter 11
upura
0
380
ダイナミックプライシング とその実例
skmr2348
3
400
Active Adaptive Experimental Design for Treatment Effect Estimation with Covariate Choices
masakat0
0
220
RSJ2024「基盤モデルの実ロボット応用」チュートリアルA(河原塚)
haraduka
3
640
20241115都市交通決起集会 趣旨説明・熊本事例紹介
trafficbrain
0
230
Weekly AI Agents News! 9月号 プロダクト/ニュースのアーカイブ
masatoto
2
140
MetricSifter:クラウドアプリケーションにおける故障箇所特定の効率化のための多変量時系列データの特徴量削減 / FIT 2024
yuukit
2
120
授業評価アンケートのテキストマイニング
langstat
1
360
Featured
See All Featured
GitHub's CSS Performance
jonrohan
1030
460k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
191
16k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
44
2.2k
Designing the Hi-DPI Web
ddemaree
280
34k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
506
140k
Building a Scalable Design System with Sketch
lauravandoore
459
33k
Designing on Purpose - Digital PM Summit 2013
jponch
115
7k
Statistics for Hackers
jakevdp
796
220k
Building an army of robots
kneath
302
43k
[RailsConf 2023] Rails as a piece of cake
palkan
52
4.9k
Practical Orchestrator
shlominoach
186
10k
Become a Pro
speakerdeck
PRO
25
5k
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)
• • • • •