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
190
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
140
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
190
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
130
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
130
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
110
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
230
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
290
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
190
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
190
Other Decks in Research
See All in Research
The many faces of AI and the role of mathematics
gpeyre
1
1.5k
言語と数理の交差点:テキストの埋め込みと構造のモデル化 (IBIS 2024 チュートリアル)
yukiar
4
1k
The Fellowship of Trust in AI
tomzimmermann
0
200
Global Evidence Summit (GES) 参加報告
daimoriwaki
0
220
The Relevance of UX for Conversion and Monetisation
itasohaakhib1
0
130
Weekly AI Agents News! 9月号 論文のアーカイブ
masatoto
1
170
2038年問題が思ったよりヤバい。検出ツールを作って脅威性評価してみた論文 | Kansai Open Forum 2024
ran350
8
3.7k
QGISハンズオン事に質問のあったProjectのGeoPackageへの保存方法についての、補足の資料です。
wata909
0
110
「熊本県内バス・電車無料デー」の振り返りとその後の展開@土木計画学SS:成功失敗事例に学ぶ公共交通運賃設定
trafficbrain
0
120
ECCV2024読み会: Minimalist Vision with Freeform Pixels
hsmtta
1
360
Weekly AI Agents News! 12月号 論文のアーカイブ
masatoto
0
130
Leveraging LLMs for Unsupervised Dense Retriever Ranking (SIGIR 2024)
kampersanda
2
280
Featured
See All Featured
Statistics for Hackers
jakevdp
797
220k
Imperfection Machines: The Place of Print at Facebook
scottboms
267
13k
Java REST API Framework Comparison - PWX 2021
mraible
28
8.3k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
132
33k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
3
240
Into the Great Unknown - MozCon
thekraken
34
1.6k
How to Ace a Technical Interview
jacobian
276
23k
Building an army of robots
kneath
302
45k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
280
13k
Site-Speed That Sticks
csswizardry
3
270
Dealing with People You Can't Stand - Big Design 2015
cassininazir
365
25k
Rebuilding a faster, lazier Slack
samanthasiow
79
8.8k
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