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
210
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
170
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
220
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
260
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
320
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
220
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
220
Other Decks in Research
See All in Research
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
shunk031
11
6.7k
Scale-Aware Recognition in Satellite images Under Resource Constraints
satai
3
260
rtrec@dbem6
myui
6
790
BtoB プロダクトにおけるインサイトマネジメントの必要性 現場ドリブンなカミナシがインサイトマネジメントに取り組むワケ / Why field-driven Kaminashi is working on insight management
kaminashi
1
440
GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization
satai
3
170
Cross-Media Information Spaces and Architectures
signer
PRO
0
220
Mechanistic Interpretability:解釈可能性研究の新たな潮流
koshiro_aoki
1
130
SSII2025 [TS2] リモートセンシング画像処理の最前線
ssii
PRO
6
2.3k
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
330
公立高校入試等に対する受入保留アルゴリズム(DA)導入の提言
shunyanoda
0
4.8k
線形判別分析のPU学習による朝日歌壇短歌の分析
masakat0
0
120
JSAI NeurIPS 2024 参加報告会(AI アライメント)
akifumi_wachi
5
1k
Featured
See All Featured
Rails Girls Zürich Keynote
gr2m
94
13k
BBQ
matthewcrist
88
9.7k
Speed Design
sergeychernyshev
30
970
Building Better People: How to give real-time feedback that sticks.
wjessup
368
19k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
45
9.6k
Code Reviewing Like a Champion
maltzj
523
40k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
8
750
Into the Great Unknown - MozCon
thekraken
39
1.8k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
12k
Responsive Adventures: Dirty Tricks From The Dark Corners of Front-End
smashingmag
252
21k
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
31
1.2k
Become a Pro
speakerdeck
PRO
28
5.4k
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