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
(Reading )Does BERT Know that the IS-A Relation...
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
ando
January 23, 2023
Science
130
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
550
Is In-hospital Meta-information Useful for Abstractive Discharge Summary Generation?
ando55
0
290
(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
78
(Reading) Predictive Adversarial Learning from Positive and Unlabeled Data
ando55
0
170
Argument Invention from First Principles
ando55
2
360
Other Decks in Science
See All in Science
TypeScript で WebAssembly を用いた 型安全なプラグイン設計
nagano
2
620
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
220
因果推論と機械学習
sshimizu2006
1
1.5k
ゲームと人工知能
miyayou
0
220
Physical AIを支えるWeights & Biases
olachinkei
1
630
2026 Introduction to University Math 01
kanaya
0
150
Where does the rigor go? Research software and the future of trustworthy science.
arfon
0
290
データベース09: 実体関連モデル上の一貫性制約
trycycle
PRO
0
1.9k
データベース10: 拡張実体関連モデル
trycycle
PRO
0
1.6k
Massey Ratings for Match Outcome Prediction in Table Tennis: Evidence of Greater Stability than the ITTF World Ranking
konakalab
0
150
チュートリアル:世界モデル
hf149
0
2.3k
データベース02: データベースの概念
trycycle
PRO
2
1.4k
Featured
See All Featured
State of Search Keynote: SEO is Dead Long Live SEO
ryanjones
0
280
Breaking role norms: Why Content Design is so much more than writing copy - Taylor Woolridge
uxyall
1
420
Keith and Marios Guide to Fast Websites
keithpitt
413
23k
Max Prin - Stacking Signals: How International SEO Comes Together (And Falls Apart)
techseoconnect
PRO
0
470
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
eileencodes
141
35k
Building a A Zero-Code AI SEO Workflow
portentint
PRO
0
730
Color Theory Basics | Prateek | Gurzu
gurzu
1
470
Measuring Dark Social's Impact On Conversion and Attribution
stephenakadiri
2
290
Speed Design
sergeychernyshev
33
2.1k
Mind Mapping
helmedeiros
1
370
Joys of Absence: A Defence of Solitary Play
codingconduct
1
530
The Hidden Cost of Media on the Web [PixelPalooza 2025]
tammyeverts
2
500
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