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
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
600
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
81
(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
自社のレビュー履歴からAIコードレビュアーをつくる方法
estie
5
1.8k
SAT ソルバーの仕組みと制約ソルバーへの応用
tsoh
3
680
Van Dare naar Durf
voginip
0
310
バランスって大事だね
akasan
1
160
ゲームと人工知能
miyayou
0
260
AlgorithAlgorihms for Decision Making
mickey_kubo
0
170
Controller Design for Symbolic Input-Output Systems Using Feedforward Neural Networks
konakalab
0
140
「念のためのログ保存」を組織全体でやめるためのポリシーと仕組み作り
i2tsuki
4
410
[Relay webinaire eBIS actu n°16] Amélioration de la survie des JB avec la génétique - Introduction
institutdelelevage
PRO
0
350
20260820_アウトカムが二値のデータに対するCausal Impact@LINEヤフー Data Science Share #2 / Causal Impact for Binary Outcomes
brainpadpr
3
1.5k
Build your own LLM, Live, with MicroGPT
ianozsvald
0
160
不動産業界における業界特化のデータ整備とAI活用 ─Vertical DataとVertical AI─
estie
1
1.1k
Featured
See All Featured
Primal Persuasion: How to Engage the Brain for Learning That Lasts
tmiket
0
500
A designer walks into a library…
pauljervisheath
211
25k
Tips & Tricks on How to Get Your First Job In Tech
honzajavorek
1
800
How to Get Subject Matter Experts Bought In and Actively Contributing to SEO & PR Initiatives.
livdayseo
0
220
Getting science done with accelerated Python computing platforms
jacobtomlinson
2
540
Why Your Marketing Sucks and What You Can Do About It - Sophie Logan
marketingsoph
0
430
How to build a perfect <img>
jonoalderson
1
6.1k
エンジニアに許された特別な時間の終わり
watany
109
250k
GitHub's CSS Performance
jonrohan
1033
470k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
35
3.8k
SEO Brein meetup: CTRL+C is not how to scale international SEO
lindahogenes
2
2.9k
Side Projects
sachag
456
43k
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