Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
文献紹介: Attention is not Explanation
Search
Yumeto Inaoka
March 19, 2019
Research
530
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
文献紹介: Attention is not Explanation
Yumeto Inaoka
March 19, 2019
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
230
文献紹介: Open Domain Web Keyphrase Extraction Beyond Language Modeling
yumeto
0
290
文献紹介: Self-Supervised_Neural_Machine_Translation
yumeto
0
200
文献紹介: Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
yumeto
0
220
文献紹介: PAWS: Paraphrase Adversaries from Word Scrambling
yumeto
0
220
文献紹介: Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
yumeto
0
340
文献紹介: EditNTS: An Neural Programmer-Interpreter Model for Sentence Simplification through Explicit Editing
yumeto
0
440
文献紹介: Decomposable Neural Paraphrase Generation
yumeto
0
260
文献紹介: Analyzing the Limitations of Cross-lingual Word Embedding Mappings
yumeto
0
300
Other Decks in Research
See All in Research
Evaluating LLM Reliability Across Facts, Evidence, and Cultures
yukiar
0
200
実例から見るLLMのマンガ理解:実務VQAタスクによる長期的文脈と視覚情報の定性評価
kzmssk
0
160
論文読み会 SNLP2026 Tau2-Bench: Evaluating Conversational Agents in a Dual-Control Environment
s_mizuki_nlp
0
280
PGDM: Physically Guided Diffusion Model for L Downscaling
satai
3
500
【中間報告】国会議員の立法・政策実務を支える環境を巡る現状と課題
polipoli
0
660
全国町字単位空き家率推定データver1.0データ仕様
microbaseinc
0
270
[ACL 2026 Demo] Fast-MIA: Efficient and Scalable Membership Inference for LLMs
upura
0
130
Sleuthcon Keynote - How Cybercriminals (ab)use AI
fr0gger
0
350
XDPerf: A High-Performance Traffic Generator Built with WASM and eBPF
takehaya
1
320
Source Code Diff Revolution
tsantalis
0
180
The story of RefactoringMiner. Slow research, long-term impact
tsantalis
0
180
HAKARI-Bench - 実運用視点での情報検索モデル評価ベンチマーク
hotchpotch
1
780
Featured
See All Featured
Collaborative Software Design: How to facilitate domain modelling decisions
baasie
1
330
Keith and Marios Guide to Fast Websites
keithpitt
413
23k
For a Future-Friendly Web
brad_frost
183
10k
The innovator’s Mindset - Leading Through an Era of Exponential Change - McGill University 2025
jdejongh
PRO
1
350
What’s in a name? Adding method to the madness
productmarketing
PRO
24
4.2k
Why Your Marketing Sucks and What You Can Do About It - Sophie Logan
marketingsoph
0
420
What does AI have to do with Human Rights?
axbom
PRO
1
2.4k
Lessons Learnt from Crawling 1000+ Websites
charlesmeaden
PRO
1
1.6k
Code Review Best Practice
trishagee
74
20k
Into the Great Unknown - MozCon
thekraken
41
2.7k
Dealing with People You Can't Stand - Big Design 2015
cassininazir
367
27k
JAMstack: Web Apps at Ludicrous Speed - All Things Open 2022
reverentgeek
1
620
Transcript
Attention is not Explanation 文献紹介 2019/03/19 長岡技術科学大学 自然言語処理研究室 稲岡 夢人
Literature 2 Title Attention is not Explanation Author Sarthak Jain,
Byron C. Wallace Conference NAACL-HLT 2019 Paper https://arxiv.org/abs/1902.10186
Abstract Attentionは入力単位で重みを示す その分布が重要性を示すものとして扱われることがある → 重みと出力の間の関係は明らかにされていない 標準的なAttentionは意味のある説明を提供しておらず、 そのように扱われるべきでないことを示す
3
調査方法 1. 重みが重要度と相関しているか 2. 事実と反する重み設定が予測を変化させるか 4
Tasks Binary Text Classification Question Answering (QA)
Natural Language Inference (NLI) 5
Datasets 6
Results 7
Definitions 出力結果の比較に使用する距離 Attentionの比較に使用する距離 8
Results Attentionの変化を大きくしても結果が変化しない → 出力への影響が小さい 9
Results DiabetesはPositiveのクラスにおいては影響が大きい → 高精度で糖尿病を示すトークンが存在するため 10
Adversarial Attention 出力を大きく変化させるようにAttentionを変化させる Attentionが少し変化しただけで出力が大きく変化するか ← Attentionの挙動を確認 12
Results 少しのAttentionの変化で出力が大きく変化している 13
Conclusions 重要度とAttentionの重みは相関が弱い 事実に反する重みは必ずしも出力を変化させない Seq2seqについては今後の課題とする 14