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: Similarity-Based Reconstruction Loss for Meaning Representation
Search
Yumeto Inaoka
May 26, 2019
Research
1
170
文献紹介: Similarity-Based Reconstruction Loss for Meaning Representation
2019/05/28の文献紹介で発表
Yumeto Inaoka
May 26, 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
120
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
160
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
87
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
260
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
180
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
160
Other Decks in Research
See All in Research
自然言語とVision&Language
kuehara
19
4.4k
SSII2024 [OS3] 企業における基盤モデル開発の実際
ssii
PRO
0
490
AIを前提とした体験の実現に向けて/toward_ai_based_experiences
monochromegane
1
430
IVILab. Research Introduction
ysugano
0
260
Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift
nanofi
3
230
Conducting AI Research on High-Performance Computing (HPC) Systems
yoshipon
2
460
SSII2024 [TS1] 生成AIと3次元ビジョン ~3次元生成AIの最先端の理論~
ssii
PRO
1
980
SSII2024 [OS1] 現場の課題を解決する ロボットラーニング
ssii
PRO
0
420
Introduction of NII S. Koyama's Lab (AY2024)
skoyamalab
0
330
SSII2024 [PD] 画像センシングの未来
ssii
PRO
0
290
[Human-AI Decision Making勉強会] 説明の更新はユーザにどのような影響をもたらすか
okoso
1
310
The past, present, and future of local-first
ept
0
390
Featured
See All Featured
Faster Mobile Websites
deanohume
303
30k
Practical Orchestrator
shlominoach
185
10k
A Modern Web Designer's Workflow
chriscoyier
689
190k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
226
52k
Principles of Awesome APIs and How to Build Them.
keavy
124
16k
The Cost Of JavaScript in 2023
addyosmani
31
4.7k
Making Projects Easy
brettharned
111
5.7k
How to Think Like a Performance Engineer
csswizardry
4
590
VelocityConf: Rendering Performance Case Studies
addyosmani
321
23k
Happy Clients
brianwarren
94
6.6k
Building a Scalable Design System with Sketch
lauravandoore
458
32k
Teambox: Starting and Learning
jrom
130
8.6k
Transcript
Similarity-Based Reconstruction Loss for Meaning Representation
Literature 2
Abstract • • • 3
Introduction • • 4
Related Work • • • • 5
Related Work • • 6
Auto-Encoder •ℒ , • • • • 7
Weighted similarity loss •ℒ = − σ =1 sim ,
• • • : • • sim() • 8
Weighted cross-entropy loss •ℒ = − σ =1 sim ,
log( ) • • 9
Soft label loss •ℒ = − σ =1 ∗log •
∗ = ൞ sim , σ =1 sim(,) , ∈ top N 0 , ∉ top N • • 10
True-label encoding 11
Tasks & Datasets • • • 12
Results 13
Results 14
Additional Experiments • • 15
Results • • 16
Results 17
Results 18
Results 19
Discussion • • 20
Conclusion • • • • 21