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
180
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
350
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
AIスパコン「さくらONE」の オブザーバビリティ / Observability for AI Supercomputer SAKURAONE
yuukit
1
370
Stealing LUKS Keys via TPM and UUID Spoofing in 10 Minutes - BSides 2025
anykeyshik
0
140
SNLP2025:Can Language Models Reason about Individualistic Human Values and Preferences?
yukizenimoto
0
190
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
520
多言語カスタマーインタビューの“壁”を越える~PMと生成AIの共創~ 株式会社ジグザグ 松野 亘
watarumatsuno
0
130
IMC の細かすぎる話 2025
smly
2
700
引力・斥力を制御可能なランダム部分集合の確率分布
wasyro
0
260
論文紹介: ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement
hisaokatsumi
0
110
長期・短期メモリを活用したエージェントの個別最適化
isidaitc
0
210
地域丸ごとデイサービス「Go トレ」の紹介
smartfukushilab1
0
250
MetaEarth: A Generative Foundation Model for Global-Scale Remote Sensing Image Generation
satai
4
340
論文紹介:Not All Tokens Are What You Need for Pretraining
kosuken
0
200
Featured
See All Featured
Automating Front-end Workflow
addyosmani
1371
200k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
PRO
190
55k
Raft: Consensus for Rubyists
vanstee
140
7.2k
A Tale of Four Properties
chriscoyier
161
23k
The Cost Of JavaScript in 2023
addyosmani
55
9.1k
Building Flexible Design Systems
yeseniaperezcruz
329
39k
Building Adaptive Systems
keathley
44
2.8k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
Designing for humans not robots
tammielis
254
26k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
48
9.7k
Making the Leap to Tech Lead
cromwellryan
135
9.6k
Being A Developer After 40
akosma
91
590k
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