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
170
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
120
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
160
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
120
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
120
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
89
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
210
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
270
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
180
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
170
Other Decks in Research
See All in Research
20240626_金沢大学_新機能集積回路設計特論_配布用 #makelsi
takasumasakazu
0
140
ニューラルネットワークの損失地形
joisino
PRO
24
9.1k
Weekly AI Agents News! 7月号 プロダクト/ニュースのアーカイブ
masatoto
0
120
大規模言語モデルを用いた日本語視覚言語モデルの評価方法とベースラインモデルの提案 【MIRU 2024】
kentosasaki
2
420
Weekly AI Agents News! 6月号 プロダクト/ニュースのアーカイブ
masatoto
0
110
LINEチャットボット「全力肯定彼氏くん(LuC4)」の 1年を振り返る
o_ob
0
1.4k
SSII2024 [OS3] 基盤モデル(オープニング)
ssii
PRO
0
320
言語処理学会30周年記念事業留学支援交流会@YANS2024:「学生のための短期留学」
a1da4
1
170
日本語医療LLM評価ベンチマークの構築と性能分析
fta98
3
380
スモールデータ勉強会発表資料
natsutan
0
580
医療分野におけるLLMの現状と応用可能性について
kento1109
11
3k
「人間にAIはどのように辿り着けばよいのか?ー 系統的汎化からの第一歩 ー」@第22回 Language and Robotics研究会
maguro27
0
510
Featured
See All Featured
Fontdeck: Realign not Redesign
paulrobertlloyd
80
5.1k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
225
22k
BBQ
matthewcrist
83
9.1k
[RailsConf 2023] Rails as a piece of cake
palkan
48
4.6k
Happy Clients
brianwarren
96
6.6k
Writing Fast Ruby
sferik
623
60k
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
354
29k
Gamification - CAS2011
davidbonilla
79
4.9k
Facilitating Awesome Meetings
lara
49
5.9k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
230
17k
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
103
48k
Designing on Purpose - Digital PM Summit 2013
jponch
113
6.8k
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