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
(Reading )Does BERT Know that the IS-A Relation...
Search
ando
January 23, 2023
Science
120
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
(Reading )Does BERT Know that the IS-A Relation Is Transitive?
Komachi lab
ando
January 23, 2023
More Decks by ando
See All by ando
博士論文公聴会資料
ando55
0
480
Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?
ando55
0
280
(読み会)Evaluating Factuality in Text Simplification
ando55
1
210
(Reading) Relational Multi-Task Learning Modeling Relations between Data and Tasks
ando55
0
200
(Reading )Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators’ Disagreement
ando55
0
180
(Reading) Preregistering NLP research
ando55
0
75
(Reading) Predictive Adversarial Learning from Positive and Unlabeled Data
ando55
0
170
Argument Invention from First Principles
ando55
2
350
Other Decks in Science
See All in Science
[NLP2026 参加報告会] AI for Science まとめ / NLP2026
lychee1223
0
2k
Bリーグのショットデータを活用した得点期待値モデルの構築 / Construction of expected points model using shot data of B.LEAGUE
konakalab
0
210
AI(人工知能)の過去・現在・未来 ~AIは人類を越えるのか~
tagtag
PRO
0
160
AIを用いた PID制御で部屋 の温度制御をしてみた
nearme_tech
PRO
0
240
AIPシンポジウム 2025年度 成果報告会 「因果推論チーム」
sshimizu2006
3
620
プロジェクト「Azayaka」のSARの数式とジオメトリ
syuchimu
0
460
医療 LLM ベンチマークの現在地:多面的評価 と日本ローカライズ
analokmaus
1
680
社内で活躍できるデータサイエンティストになるために
aikinohara
1
160
データベース11: 正規化(1/2) - 望ましくない関係スキーマ
trycycle
PRO
0
1.7k
第67回コンピュータビジョン勉強会論文紹介「RoboWheel: A Data Engine from Real-World Human Demonstrations for Cross-Embodiment Robotic Learning」
x_ttyszk
0
180
機械学習 - pandas入門
trycycle
PRO
0
700
水耕栽培:古代の知恵から宇宙農業まで
grow_design_lab
0
220
Featured
See All Featured
Ethics towards AI in product and experience design
skipperchong
2
360
Jamie Indigo - Trashchat’s Guide to Black Boxes: Technical SEO Tactics for LLMs
techseoconnect
PRO
0
640
The Cost Of JavaScript in 2023
addyosmani
55
10k
Documentation Writing (for coders)
carmenintech
77
5.5k
The Pragmatic Product Professional
lauravandoore
37
7.4k
New Earth Scene 8
popppiees
3
2.5k
Cheating the UX When There Is Nothing More to Optimize - PixelPioneers
stephaniewalter
287
14k
So, you think you're a good person
axbom
PRO
2
2.1k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
Building AI with AI
inesmontani
PRO
1
1.2k
HTML-Aware ERB: The Path to Reactive Rendering @ RubyCon 2026, Rimini, Italy
marcoroth
4
540
Reality Check: Gamification 10 Years Later
codingconduct
0
2.3k
Transcript
ACL2022 Short paper
- #&35͕*4"ؔͷ5SBOTJUJWFੑ࣭ͱͲͷఔҰக͢Δ͔ΛఆྔԽɻ - #&35ͷ༧ଌ*4"ؔͷਪҠੑʹશʹैΘͳ͍͜ͱ͕໌Β͔ʹͳͬͨ 5SBOTJUJWF A is-a B & →
A is-a C︖ B is-a C - #&35*4"ؔΛͷ"DDVSBDZͰ༧ଌͰ͖Δ - #&35͕"JTB#ͱ#JTB$Λਖ਼͘͠༧ଌͨ͠߹ɺ"JTB$ ˠͦͷ··ࣝϕʔεͱͯ͠ѻ͑ͳ͍ 2 概要
- ໊ࢺΛ༻͍Δ 3 Task definition 語義のペア Is-aであれば1, でなければ0
-\TcT㱨4 BOEIZQP T 㱵 ^ 8PSE/FUͷશͯͷϦʔϑηϯεɻ 48PSE/FUͷશͯͷޠٛͷू߹ɺIZQP T ҙຯTͷԼҐޠٛͷू߹Λද͢ɻ -
*4"ΛऔΓग़͢ • -͔ΒMFBGͷޠٛ/ΛϥϯμϜʹநग़͠ɺ/ΛSPPU3ʹଓͯ͠ɺύεQ /ˠ3 Λಘ Δ Q͔Β"ɺ#ɺ$ͷͭͷޠٛΛϥϯμϜʹநग़͠ɺ"ɺ#ɺ$ͷޠٛͷྫจΛಘΔ ͜ͷ݁Ռɺλϓϧʢ"ɺ#ɺ$ʣͱͭͷਖ਼ྫʢ"ɺ#ʣɺʢ#ɺ$ʣɺʢ"ɺ$ʣ͕ಘ ΒΕΔɻ - /PU*4"ΛऔΓग़͢ • -͔Βೋͭͷ/ /ΛϥϯμϜʹநग़͠ɺೋͭͷύεQ /ˠ3 ͱQ /ˠ3 Λ ಘΔQɺQ͔ΒͦΕͧΕ"⒌ɺ#⒌ΛϥϯμϜʹαϯϓϦϯά͠ɺޠٛ"⒌ɺ#⒌ͷྫจΛಘ Δ "⒌͕#⒌ˠ3ͷύε্ʹͳ͍߹ɺ·ͨͦͷٯͷ߹ɺෛྫʢ"⒌ #⒌ʣΛಘΔ - σʔληοτͰɺݸͷλϓϧ͕͋Γɺݸͷਖ਼ྫͱݸͷෛྫ͕͋Δɻ 4 Positive, Negative example抽出
- #&35ͷ࠷ऴͷϕΫτϧΛ༻ʢTVCXPSEBWFSBHFʣ - #&35ϑΝΠϯνϡʔχϯά͠ͳ͍ɺ࠷ۙʢOOʣྨثΛ༻ ˠγϯϓϧͳͷΛ͍͍ͨ - ϢʔΫϦουڑΛڑࢦඪͱͯ͠༻͍Δɻ 5 分類 語義2
語義1
- ςετηοτͰɺ " # ͱ # $ ͷฏۉϗοϓͦΕͧΕ ͱ Ͱ͋ͬͨɻ
- ͜ͷࠩɺ8PSE/FUͷྫจΛ࣋ͭޠ͕ٛۉʹ͍ͯ͠ͳ͍͜ͱʹىҼ͍ͯ͠Δɻ ʢ্ҐޠྫจΛ͍͍࣋ͬͯ͢ʣ 6 Hop数
- ϗοϓ͕গͳ͍߹ʢʣɺϗοϓ͕ଟ͍߹ʢʣΑΓߴ͍ਫ਼Ͱ*4"ؔ Λ༧ଌͰ͖Δ - ϗοϓ͕૿Ճͯ͠༧ଌਫ਼େ͖͘ԼͤͣɺϗοϓͰਫ਼ʹେ͖ͳΒ͖ͭ ͳ͍ɻ 7 実験結果 ?
- #&35͕ʢ"ɺ#ʣɺʢ#ɺ$ʣΛਖ਼͘͠༧ଌͨ͠߹ʹɺ*4"ؔʢ"ɺ$ʣΛਖ਼͘͠༧ଌ ͢ΔසΛଌఆ - Q "# ͷ " # ͷ͏ͪɺਖ਼͘͠༧ଌ͞Εͨ
" # ͷׂ߹ - Q "$c"# #$ ɺ " # ͱ # $ ͕ਖ਼͘͠༧ଌ͞ΕΔ߹ɺ " $ ͕ਖ਼͘͠༧ଌ͞ΕΔׂ߹ - "JTB$͕ৗʹਖ਼͘͠༧ଌ͞Εͳ͍͜ͱɺ#&35͕ཧతʹҰ؏ͨ͠༧ଌΛ͢ΔೳྗΛ ͍͍ܽͯΔ͜ͱΛ͍ࣔࠦͯ͠Δɻ 8 Prediction Ability for Transitivity