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
B3_Seminar_6
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
kakubari
March 10, 2017
Technology
85
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
B3_Seminar_6
長岡技術科学大学
自然言語処理研究室
角張竜晴
kakubari
March 10, 2017
More Decks by kakubari
See All by kakubari
動詞クエリの語間の関係性に基づくクエリマイニング
kakubari
0
130
Neural Modeling of Multi-Predicate Interactions for Japanese Predicate Argument Structure Analysis
kakubari
1
190
Leveraging Crowdsourcing for Paraphrase Recognition
kakubari
0
110
Automatically Acquired Lexical Knowledge Improves Japanese Joint Morphological and Dependency Analysis
kakubari
0
120
Labeling the Semantic Roles of Commas
kakubari
0
110
Integrating Case Frame into Japanese to Chinese Hierarchical Phrase-based Translation Model
kakubari
0
130
Improving Chinese Semantic Role Labelingusing High-quality Surface and Deep Case Frames
kakubari
0
99
Exploring Verb Frames for Sentence Simplification in Hindi
kakubari
0
160
述語項構造と照応関係のアノテーション
kakubari
0
270
Other Decks in Technology
See All in Technology
Genie Code ワークショップ 基礎編 / Genie-Code-Workshop-fundamental
databricksjapan
PRO
0
360
PM領域でのAI Agentの活用
lycorptech_jp
PRO
0
270
AIで開発は速くなったのに、なぜ現場は楽にならないのか 〜あなたの組織のボトルネックを突き止めるワークショップ〜
jacopen
1
270
なぜSRE・セキュリティは評価されないのか?守りの組織を事業成長エンジンに変えた実践
cscengineer
PRO
3
2.3k
[DroidKaigi 2026] Making UI specifications visible: Android UI development in the AI agent era supported by Compose Screenshot Testing and galleries
syarihu
0
580
enechainの内製セルフサービスプラットフォーム
hiyosi
0
120
推論の観測、できていますか? 〜 Google Cloud Gemini Enterprise Agent Platformで 3つの Gemini モデルを実測して踏んだ、評価の罠 〜
shukob
PRO
0
150
Where Is JetBrains AI Heading- — Central CLI, Air Alpha, and the Agentic Development Stack
x5gtrn
PRO
0
140
スクラムで身についていた動き方を、XPで捉え直してみた
codmoninc
PRO
1
250
プロダクトエンジニアに必要な「いい感じ」に作る能力 〜たくさん作れる時代に、どこまで作るかの決め方〜
jnishime_dresscode
2
1.4k
プロダクト思考 × 基盤思考を AIで実現する Compound Engineering
tkc66buzz
1
280
Sony-DroidKaigi2026
sony
1
320
Featured
See All Featured
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
49
10k
Six Lessons from altMBA
skipperchong
29
4.5k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.8k
Practical Orchestrator
shlominoach
191
12k
We Have a Design System, Now What?
morganepeng
55
8.3k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
23k
Avoiding the “Bad Training, Faster” Trap in the Age of AI
tmiket
0
230
Lightning talk: Run Django tests with GitHub Actions
sabderemane
0
250
Ten Tips & Tricks for a 🌱 transition
stuffmc
0
200
Stewardship and Sustainability of Urban and Community Forests
pwiseman
0
510
A Soul's Torment
seathinner
7
3.5k
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.5k
Transcript
Ԭٕज़Պֶେֶ ిؾిࢠใֶ՝ఔ ֶ෦ɹ֯ுཽ ࣗવݴޠݚڀࣨ ɹ#̏θϛ ʙୈճʙ ใΞΫηεධՁํ๏
目次 ˔͡Ίʹ ˔جຊత༻ޠͷఆٛ ˔ใΞΫηεγεςϜͷධՁ ˔ద߹ੑఆͷલఏ ˔࠶ݱͱਫ਼ʢద߹ʣ
はじめに త ใݕࡧγεςϜΛݚڀऀ͕దͳํ๏ͰධՁ͠ɺ݈ શͳٕज़ਐาʹߩݙ͢ΔͨΊͷಓےΛࣔ͢ طଘͷධՁࢦඪΛཧղ͠ɺదͳͷΛબͰ͖ΔΑ ͏ʹͳΔ ใࠂॻΛॻ͘͜ͱʹʹཱͭ
基本的用語の定義 ˔ใݕࡧγεςϜ ɹਓؒ͘͠ػցʢ྆͘͠ํʣ͕ద༻͢Δنଇٴͼखଓ ͖ͷू߹ ˔ใݕࡧγεςϜͷׂ ɹϢʔβͷใཁٻΛຬͨ͢จॻʹͦͷϢʔβΛಋ͘͜ͱ ˔ใཁٻ ɹϢʔβ͕͋ΔతΛୡ͢ΔͨΊʹݱࡏ͍࣋ͬͯΔࣝͰ
ෆेͰ͋Δͱײ͍ͯ͡Δঢ়ଶ ˔ݕࡧཁٻ ɹϢʔβͷใཁٻΛςΩετͷܗͰ໌จԽͨ͠ͷ
基本的用語の定義 ˔ద߹ੑ ɹϢʔβͷཁٻʹจॻ͕ͲΕ΄Ͳྑ͘Ϛον͍ͯ͠Δ ͔ ʙใݕࡧධՁͷతʙ ɹϢʔβͷใཁٻΛຬͨͨ͢ΊʹΑΓޮՌతͳγε ςϜΛߏங͢Δ͜ͱ γεςϜΛ٬؍తʹධՁ͠ɺٕज़ਐาΛଅ͢
基本的用語の定義 ใݕࡧγεςϜͷग़ྗ݁Ռͷܗଶ ˔ू߹ݕࡧ ɹೖྗ͞ΕͨΫΤϦʹରͯ͠จॻͷू߹Λग़ྗ͢Δͷ ɹྫ͑ʜ ɹɾಛڐௐࠪͷΑ͏ʹඞཁͳจॻΛݕࡧ ˔ϥϯΫ͖ͭݕࡧ ɹจॻΛͳΜΒ͔ͷํ๏ʹΑΓॱং͚ͮͯग़ྗ͢Δͷ
ɹྫ͑ʜ ɹɾΣϒݕࡧΤϯδϯ
基本的用語の定義 ˔ใΞΫηε ɹϢʔβͷใཁٻΛຬͨͨ͢Ίͷٕज़ͷ૯শ ɹྫ͑ʜ ɹɾςΩετཁ ɹɾ࣭Ԡ ɹɾςΩετྨ ɹɾػց༁
情報アクセスシステムの評価 ඃݧऀ࣮ݧΛͱʹ࣮ࡍͷϢʔβ͕ݕࡧͨ͠ใͷ ࣭ݕࡧͷޮΛ͡ΔΞϓϩʔν ɹখنʹͳΓ͕ͪͰɺ࠶ݱՄೳੑ͕อূͰ͖ͳ͍ ɹ݁ՌͷҰൠԽ͕͠ʹ͍͘ ςετίϨΫγϣϯͱ͍͏ධՁ༻ͷσʔληοτΛ
ධՁࢦඪͱڞʹ༻͍ΔΞϓϩʔν ɹେن͔ͭ࠶ݱՄೳͳ࣮ݧΛߦ͑Δ ɹ Ὃ ɹదͳධՁࢦඪΛબఆ͠ɺదͳํ๏Ͱ༻͢Δ
適合性判定の前提 ˔ద߹ੑͷಠཱੑ ɹ༩͑ΒΕͨݕࡧཁٻʹର͢Δݸʑͷจॻͷద߹ੑɺ ͦͷݕࡧཁٻٴͼͦͷจॻͷΈʹґଘ͢Δ ɾଞͷจॻͷӨڹΛड͚ͳ͍ ɾݕࡧཁٻࣗମ͕มԽ͠ͳ͍ݶΓɺద߹ੑෆม
適合性判定の前提 ˔ద߹ੑͱ༗༻ੑͷҧ͍ ᾇݕࡧཁٻʹର͢Δจॻͷద߹ੑɺจॻίϨΫγϣϯதͷ ଞͷจॻ͔ΒಠཱͰ͋Δɻ ᾈݕࡧཁٻऀʹͱͬͯͷద߹จॻͷ༗༻ੑɺݕࡧཁٻऀ͕ ͢Ͱʹݟͨద߹จॻʹґଘ͢Δ͔͠Εͳ͍ɻ ద߹ੑ༗༻ੑͷඞཁ݅ʹ͗͢ͳ͍ɻ
適合性判定の前提 ˔ఆऀؒෆҰக ɹͲΜͳʹৄࡉʹ໌จԽ͞ΕͨݕࡧཁٻͰ͋ͬͯɺ ͜Εʹର͢Δద߹ੑఆ݁ՌඞવతʹఆऀʹΑͬ ͯҟͳΔ ˔ఆऀෆҰக ɹఆऀ͕࣭ऀࣗͰ͋ͬͨͱͯ͠ఆΛߦ͏࣌ ʹΑͬͯҟͳΔՄೳੑ͕͋Δ
適合性判定の前提 ˔૬ରత࠶ݱ ɹਅͷద߹จॻͷΘΓʹɺෳͷखஈʹΑΓಘͨ ద߹จॻू߹ͷू߹ͷେ͖͞Λ༻͍ͯܭࢉͨ͠࠶ݱ ʢଈͪɺݕࡧӮΕͷগͳ͞ʣ
再現率と精度 "ɿద߹ੑఆʹΑΓఆٛ͞Ε͍ͯΔద߹จॻͷू߹ #ɿใݕࡧγεςϜ͕ݕࡧͨ͠จॻͷू߹ "㱯#ɿݕࡧ͞Εͨద߹จॻ ˔࠶ݱʢ3FDʣɿݕࡧӮΕͷগͳ͞ ˔ਫ਼ʢ1SFDʣɿݕࡧޡΓͷগͳ͞ʢద߹ʣ
Pec = A ∩ B A Prec = A ∩ B B
参考文献 ˔ใΞΫηεධՁํ๏ɺञҪɺ ɹίϩφࣾɺ݄