Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
文献紹介: Similarity-Based Reconstruction Loss for ...
Search
Yumeto Inaoka
May 26, 2019
Research
270
1
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
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
Transcript
21 slides
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
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
230
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
300
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
200
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
220
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
250
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
340
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
440
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
260
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
310
Other Decks in Research
See All in Research
生成AI時代の開発方法論と、メールサーバー運用の新しいかたち
hirachan
0
240
Kunai: Toward a Verifier-Safe Layered DSL for Nested Encapsulation Packet Filtering on eBPF
takehaya
1
210
GeoAgent勉強会 論文紹介と強い推論モデルが与えるインパクト
satai
5
490
ros2-perf-multihost: Automated Coordination Framework for Objective Architecture Evaluation in Distributed Systems
takasehideki
0
180
[SNLP2026] Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
wataruuuuu
0
370
[CV勉強会@関東 CVPR2026] PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow / kantocv 67th CVPR 2026
shunk031
0
410
完全自律LLMエージェントでDIVER OSINT CTF 2026に挑戦してみた
analokmaus
0
830
Pesée et pointage par imagerie 3D : PHENO3D entre en phase de test terrains
institutdelelevage
PRO
0
120
生成AIなんでも展示会vol6 LT登壇資料 NexteraBERT
rikkabotan7
0
220
SPACE 2026 - Femmes en Elevage – Regards croisés desdifférentes filières
institutdelelevage
PRO
0
120
湯村研究室の紹介2026 / yumulab2026
yumulab
PRO
0
230
量子サマースクール2026「量子計算機アーキテクチャ分野の概観」
youten622
1
1k
Featured
See All Featured
Navigating the Design Leadership Dip - Product Design Week Design Leaders+ Conference 2024
apolaine
2
530
Digital Projects Gone Horribly Wrong (And the UX Pros Who Still Save the Day) - Dean Schuster
uxyall
2
3.9k
Reflections from 52 weeks, 52 projects
jeffersonlam
356
22k
Agile that works and the tools we love
rasmusluckow
331
22k
RailsConf 2023
tenderlove
30
1.6k
More Than Pixels: Becoming A User Experience Designer
marktimemedia
3
630
Conquering PDFs: document understanding beyond plain text
inesmontani
PRO
4
3.3k
Leadership Guide Workshop - DevTernity 2021
reverentgeek
1
430
Joys of Absence: A Defence of Solitary Play
codingconduct
1
580
Building Better People: How to give real-time feedback that sticks.
wjessup
371
20k
Building a A Zero-Code AI SEO Workflow
portentint
PRO
0
840
ReactJS: Keep Simple. Everything can be a component!
pedronauck
666
130k