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 ...
Search
Yumeto Inaoka
May 26, 2019
Research
1
220
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
190
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
240
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
160
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
170
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
160
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
280
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
340
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
230
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
230
Other Decks in Research
See All in Research
Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
satai
3
220
一人称視点映像解析の最先端(MIRU2025 チュートリアル)
takumayagi
6
3.4k
Delta Airlines® Customer Care in the U.S.: How to Reach Them Now
bookingcomcustomersupportusa
0
110
まずはここから:Overleaf共同執筆・CopilotでAIコーディング入門・Codespacesで独立環境
matsui_528
2
470
Towards a More Efficient Reasoning LLM: AIMO2 Solution Summary and Introduction to Fast-Math Models
analokmaus
2
780
AIグラフィックデザインの進化:断片から統合(One Piece)へ / From Fragment to One Piece: A Survey on AI-Driven Graphic Design
shunk031
0
430
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
360
Vision and LanguageからのEmbodied AIとAI for Science
yushiku
PRO
1
520
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
shunk031
16
9.8k
EcoWikiRS: Learning Ecological Representation of Satellite Images from Weak Supervision with Species Observation and Wikipedia
satai
3
120
Cross-Media Information Spaces and Architectures
signer
PRO
0
240
[CV勉強会@関東 CVPR2025] VLM自動運転model S4-Driver
shinkyoto
2
480
Featured
See All Featured
A designer walks into a library…
pauljervisheath
207
24k
Music & Morning Musume
bryan
46
6.8k
How GitHub (no longer) Works
holman
315
140k
The Language of Interfaces
destraynor
161
25k
How to Ace a Technical Interview
jacobian
279
23k
Become a Pro
speakerdeck
PRO
29
5.5k
VelocityConf: Rendering Performance Case Studies
addyosmani
332
24k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
358
30k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
50k
Building Applications with DynamoDB
mza
96
6.6k
A Modern Web Designer's Workflow
chriscoyier
696
190k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
31
2.5k
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