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
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
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
PHTalks Bengaluru - SSRF When All Else Fails
dk999
0
1.2k
2025年度秋葉原ウォーカブルプロジェクト調査報告 「アキバらしいウォーカブル」とは何か
izumiyama_lab
1
240
生成AIなんでも展示会vol6 LT登壇資料 NexteraBERT
rikkabotan7
0
160
The story of RefactoringMiner. Slow research, long-term impact
tsantalis
0
180
CDCL を用いた MILP の厳密解法
imai448
0
280
PGDM: Physically Guided Diffusion Model for L Downscaling
satai
3
500
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
Karkada さんの論文 × 2 の紹介: (1) Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models, (2) Symmetry in language statistics shapes the geometry of model representations
eumesy
PRO
1
800
【ローカルAIに向き合う展示会vol.2】液体時間定数型モジュールを用いた オリジナルの双方向エンコーダーモデルNexteraBERT 推論速度向上検討並びにダウンストリーム評価
rikkabotan7
0
220
JPA2026_NetworkTutorial_JunKashihara
junkashihara
0
200
XDPerf: A High-Performance Traffic Generator Built with WASM and eBPF
takehaya
1
320
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
RailsConf 2023
tenderlove
30
1.6k
Groundhog Day: Seeking Process in Gaming for Health
codingconduct
0
380
[Rails World 2026] Durable orchestration on Rails: from continuation to workflow
palkan
1
400
The B2B funnel & how to create a winning content strategy
katarinadahlin
PRO
1
550
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
33
5k
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2.5k
The Mindset for Success: Future Career Progression
greggifford
PRO
0
520
We Analyzed 250 Million AI Search Results: Here's What I Found
joshbly
1
2k
brightonSEO & MeasureFest 2025 - Winning Strategies for Black Friday CRO & PPC - Christian Goodrich
cargoodrich
3
860
The Spectacular Lies of Maps
axbom
PRO
1
1.1k
The Cult of Friendly URLs
andyhume
79
7k
Ten Tips & Tricks for a 🌱 transition
stuffmc
1
240
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