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
200
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
160
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
210
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
140
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
150
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
130
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
250
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
310
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
210
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
210
Other Decks in Research
See All in Research
[輪講] Transformer Layers as Painters
nk35jk
4
760
20250226 NLP colloquium: "SoftMatcha: 10億単語規模コーパス検索のための柔らかくも高速なパターンマッチャー"
de9uch1
0
350
Data-centric AI勉強会 「ロボットにおけるData-centric AI」
haraduka
0
570
2025年度 生成AIの使い方/接し方
hkefka385
0
490
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
2.4k
言語モデルの内部機序:解析と解釈
eumesy
PRO
37
16k
20241226_くまもと公共交通新時代シンポジウム
trafficbrain
0
500
ドローンやICTを活用した持続可能なまちづくりに関する研究
nro2daisuke
0
200
知識強化言語モデルLUKE @ LUKEミートアップ
ikuyamada
0
390
Weekly AI Agents News! 12月号 プロダクト/ニュースのアーカイブ
masatoto
0
370
SpectralMamba: Efficient Mamba for Hyperspectral Image Classification
satai
3
300
Self-supervised audiovisual representation learning for remote sensing data
satai
3
120
Featured
See All Featured
How STYLIGHT went responsive
nonsquared
100
5.5k
A Tale of Four Properties
chriscoyier
158
23k
[RailsConf 2023] Rails as a piece of cake
palkan
54
5.4k
Code Reviewing Like a Champion
maltzj
523
40k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
135
33k
GraphQLとの向き合い方2022年版
quramy
46
14k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
29
1.6k
Documentation Writing (for coders)
carmenintech
69
4.7k
Typedesign – Prime Four
hannesfritz
41
2.6k
The World Runs on Bad Software
bkeepers
PRO
68
11k
Build your cross-platform service in a week with App Engine
jlugia
230
18k
The Language of Interfaces
destraynor
157
25k
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